Shenghua Gao

Zibo Zhao, Wen Liu, Xin Chen et al. · deepmind, tencent-ai

We present a novel alignment-before-generation approach to tackle the challenging task of generating general 3D shapes based on 2D images or texts. Directly learning a conditional generative model from images or texts to 3D shapes is prone to producing inconsistent results with the conditions because 3D shapes have an additional dimension whose distribution significantly differs from that of 2D images and texts. To bridge the domain gap among the three modalities and facilitate multi-modal-conditioned 3D shape generation, we explore representing 3D shapes in a shape-image-text-aligned space. Our framework comprises two models: a Shape-Image-Text-Aligned Variational Auto-Encoder (SITA-VAE) and a conditional Aligned Shape Latent Diffusion Model (ASLDM). The former model encodes the 3D shapes into the shape latent space aligned to the image and text and reconstructs the fine-grained 3D neural fields corresponding to given shape embeddings via the transformer-based decoder. The latter model learns a probabilistic mapping function from the image or text space to the latent shape space. Our extensive experiments demonstrate that our proposed approach can generate higher-quality and more diverse 3D shapes that better semantically conform to the visual or textural conditional inputs, validating the effectiveness of the shape-image-text-aligned space for cross-modality 3D shape generation.

Ruoyu Wang, Zehao Yu, Shenghua Gao

Multiple near frontal-parallel planes based depth representation demonstrated impressive results in self-supervised monocular depth estimation (MDE). Whereas, such a representation would cause the discontinuity of the ground as it is perpendicular to the frontal-parallel planes, which is detrimental to the identification of drivable space in autonomous driving. In this paper, we propose the PlaneDepth, a novel orthogonal planes based presentation, including vertical planes and ground planes. PlaneDepth estimates the depth distribution using a Laplacian Mixture Model based on orthogonal planes for an input image. These planes are used to synthesize a reference view to provide the self-supervision signal. Further, we find that the widely used resizing and cropping data augmentation breaks the orthogonality assumptions, leading to inferior plane predictions. We address this problem by explicitly constructing the resizing cropping transformation to rectify the predefined planes and predicted camera pose. Moreover, we propose an augmented self-distillation loss supervised with a bilateral occlusion mask to boost the robustness of orthogonal planes representation for occlusions. Thanks to our orthogonal planes representation, we can extract the ground plane in an unsupervised manner, which is important for autonomous driving. Extensive experiments on the KITTI dataset demonstrate the effectiveness and efficiency of our method. The code is available at https://github.com/svip-lab/PlaneDepth.

Sixun Dong, Huazhang Hu, Dongze Lian et al.

Sequential video understanding, as an emerging video understanding task, has driven lots of researchers' attention because of its goal-oriented nature. This paper studies weakly supervised sequential video understanding where the accurate time-stamp level text-video alignment is not provided. We solve this task by borrowing ideas from CLIP. Specifically, we use a transformer to aggregate frame-level features for video representation and use a pre-trained text encoder to encode the texts corresponding to each action and the whole video, respectively. To model the correspondence between text and video, we propose a multiple granularity loss, where the video-paragraph contrastive loss enforces matching between the whole video and the complete script, and a fine-grained frame-sentence contrastive loss enforces the matching between each action and its description. As the frame-sentence correspondence is not available, we propose to use the fact that video actions happen sequentially in the temporal domain to generate pseudo frame-sentence correspondence and supervise the network training with the pseudo labels. Extensive experiments on video sequence verification and text-to-video matching show that our method outperforms baselines by a large margin, which validates the effectiveness of our proposed approach. Code is available at https://github.com/svip-lab/WeakSVR

Binbin Huang, Xinhao Yan, Anpei Chen et al. · eth-zurich

We present an efficient frequency-based neural representation termed PREF: a shallow MLP augmented with a phasor volume that covers significant border spectra than previous Fourier feature mapping or Positional Encoding. At the core is our compact 3D phasor volume where frequencies distribute uniformly along a 2D plane and dilate along a 1D axis. To this end, we develop a tailored and efficient Fourier transform that combines both Fast Fourier transform and local interpolation to accelerate naïve Fourier mapping. We also introduce a Parsvel regularizer that stables frequency-based learning. In these ways, Our PREF reduces the costly MLP in the frequency-based representation, thereby significantly closing the efficiency gap between it and other hybrid representations, and improving its interpretability. Comprehensive experiments demonstrate that our PREF is able to capture high-frequency details while remaining compact and robust, including 2D image generalization, 3D signed distance function regression and 5D neural radiance field reconstruction.

Jiale Xu, Xintao Wang, Weihao Cheng et al.

Recent CLIP-guided 3D optimization methods, such as DreamFields and PureCLIPNeRF, have achieved impressive results in zero-shot text-to-3D synthesis. However, due to scratch training and random initialization without prior knowledge, these methods often fail to generate accurate and faithful 3D structures that conform to the input text. In this paper, we make the first attempt to introduce explicit 3D shape priors into the CLIP-guided 3D optimization process. Specifically, we first generate a high-quality 3D shape from the input text in the text-to-shape stage as a 3D shape prior. We then use it as the initialization of a neural radiance field and optimize it with the full prompt. To address the challenging text-to-shape generation task, we present a simple yet effective approach that directly bridges the text and image modalities with a powerful text-to-image diffusion model. To narrow the style domain gap between the images synthesized by the text-to-image diffusion model and shape renderings used to train the image-to-shape generator, we further propose to jointly optimize a learnable text prompt and fine-tune the text-to-image diffusion model for rendering-style image generation. Our method, Dream3D, is capable of generating imaginative 3D content with superior visual quality and shape accuracy compared to state-of-the-art methods.

Shuo Wang, Jing Li, Zibo Zhao et al.

Holistic scene understanding includes semantic segmentation, surface normal estimation, object boundary detection, depth estimation, etc. The key aspect of this problem is to learn representation effectively, as each subtask builds upon not only correlated but also distinct attributes. Inspired by visual-prompt tuning, we propose a Task-Specific Prompts Transformer, dubbed TSP-Transformer, for holistic scene understanding. It features a vanilla transformer in the early stage and tasks-specific prompts transformer encoder in the lateral stage, where tasks-specific prompts are augmented. By doing so, the transformer layer learns the generic information from the shared parts and is endowed with task-specific capacity. First, the tasks-specific prompts serve as induced priors for each task effectively. Moreover, the task-specific prompts can be seen as switches to favor task-specific representation learning for different tasks. Extensive experiments on NYUD-v2 and PASCAL-Context show that our method achieves state-of-the-art performance, validating the effectiveness of our method for holistic scene understanding. We also provide our code in the following link https://github.com/tb2-sy/TSP-Transformer.

Xianing Chen, Qiong Cao, Yujie Zhong et al.

Transformers are successfully applied to computer vision due to their powerful modeling capacity with self-attention. However, the excellent performance of transformers heavily depends on enormous training images. Thus, a data-efficient transformer solution is urgently needed. In this work, we propose an early knowledge distillation framework, which is termed as DearKD, to improve the data efficiency required by transformers. Our DearKD is a two-stage framework that first distills the inductive biases from the early intermediate layers of a CNN and then gives the transformer full play by training without distillation. Further, our DearKD can be readily applied to the extreme data-free case where no real images are available. In this case, we propose a boundary-preserving intra-divergence loss based on DeepInversion to further close the performance gap against the full-data counterpart. Extensive experiments on ImageNet, partial ImageNet, data-free setting and other downstream tasks prove the superiority of DearKD over its baselines and state-of-the-art methods.

Jiaben Chen, Yichen Zhu, Dongze Lian et al. · tsinghua

Dynamic vision sensors or event cameras provide rich complementary information for video frame interpolation. Existing state-of-the-art methods follow the paradigm of combining both synthesis-based and warping networks. However, few of those methods fully respect the intrinsic characteristics of events streams. Given that event cameras only encode intensity changes and polarity rather than color intensities, estimating optical flow from events is arguably more difficult than from RGB information. We therefore propose to incorporate RGB information in an event-guided optical flow refinement strategy. Moreover, in light of the quasi-continuous nature of the time signals provided by event cameras, we propose a divide-and-conquer strategy in which event-based intermediate frame synthesis happens incrementally in multiple simplified stages rather than in a single, long stage. Extensive experiments on both synthetic and real-world datasets show that these modifications lead to more reliable and realistic intermediate frame results than previous video frame interpolation methods. Our findings underline that a careful consideration of event characteristics such as high temporal density and elevated noise benefits interpolation accuracy.

Huazhang Hu, Sixun Dong, Yiqun Zhao et al.

Counting repetitive actions are widely seen in human activities such as physical exercise. Existing methods focus on performing repetitive action counting in short videos, which is tough for dealing with longer videos in more realistic scenarios. In the data-driven era, the degradation of such generalization capability is mainly attributed to the lack of long video datasets. To complement this margin, we introduce a new large-scale repetitive action counting dataset covering a wide variety of video lengths, along with more realistic situations where action interruption or action inconsistencies occur in the video. Besides, we also provide a fine-grained annotation of the action cycles instead of just counting annotation along with a numerical value. Such a dataset contains 1,451 videos with about 20,000 annotations, which is more challenging. For repetitive action counting towards more realistic scenarios, we further propose encoding multi-scale temporal correlation with transformers that can take into account both performance and efficiency. Furthermore, with the help of fine-grained annotation of action cycles, we propose a density map regression-based method to predict the action period, which yields better performance with sufficient interpretability. Our proposed method outperforms state-of-the-art methods on all datasets and also achieves better performance on the unseen dataset without fine-tuning. The dataset and code are available.

Ziming Zhong, Yanxu Xu, Jing Li et al.

We present MeshSegmenter, a simple yet effective framework designed for zero-shot 3D semantic segmentation. This model successfully extends the powerful capabilities of 2D segmentation models to 3D meshes, delivering accurate 3D segmentation across diverse meshes and segment descriptions. Specifically, our model leverages the Segment Anything Model (SAM) model to segment the target regions from images rendered from the 3D shape. In light of the importance of the texture for segmentation, we also leverage the pretrained stable diffusion model to generate images with textures from 3D shape, and leverage SAM to segment the target regions from images with textures. Textures supplement the shape for segmentation and facilitate accurate 3D segmentation even in geometrically non-prominent areas, such as segmenting a car door within a car mesh. To achieve the 3D segments, we render 2D images from different views and conduct segmentation for both textured and untextured images. Lastly, we develop a multi-view revoting scheme that integrates 2D segmentation results and confidence scores from various views onto the 3D mesh, ensuring the 3D consistency of segmentation results and eliminating inaccuracies from specific perspectives. Through these innovations, MeshSegmenter offers stable and reliable 3D segmentation results both quantitatively and qualitatively, highlighting its potential as a transformative tool in the field of 3D zero-shot segmentation. The code is available at \url{https://github.com/zimingzhong/MeshSegmenter}.

Chunlin Yu, Ye Shi, Zimo Liu et al.

Lifelong person re-identification (LReID) is in significant demand for real-world development as a large amount of ReID data is captured from diverse locations over time and cannot be accessed at once inherently. However, a key challenge for LReID is how to incrementally preserve old knowledge and gradually add new capabilities to the system. Unlike most existing LReID methods, which mainly focus on dealing with catastrophic forgetting, our focus is on a more challenging problem, which is, not only trying to reduce the forgetting on old tasks but also aiming to improve the model performance on both new and old tasks during the lifelong learning process. Inspired by the biological process of human cognition where the somatosensory neocortex and the hippocampus work together in memory consolidation, we formulated a model called Knowledge Refreshing and Consolidation (KRC) that achieves both positive forward and backward transfer. More specifically, a knowledge refreshing scheme is incorporated with the knowledge rehearsal mechanism to enable bi-directional knowledge transfer by introducing a dynamic memory model and an adaptive working model. Moreover, a knowledge consolidation scheme operating on the dual space further improves model stability over the long term. Extensive evaluations show KRC's superiority over the state-of-the-art LReID methods on challenging pedestrian benchmarks.

Jinpeng Yu, Binbin Huang, Yuxuan Zhang et al.

Point cloud completion aims to recover accurate global geometry and preserve fine-grained local details from partial point clouds. Conventional methods typically predict unseen points directly from 3D point cloud coordinates or use self-projected multi-view depth maps to ease this task. However, these gray-scale depth maps cannot reach multi-view consistency, consequently restricting the performance. In this paper, we introduce a GeoFormer that simultaneously enhances the global geometric structure of the points and improves the local details. Specifically, we design a CCM Feature Enhanced Point Generator to integrate image features from multi-view consistent canonical coordinate maps (CCMs) and align them with pure point features, thereby enhancing the global geometry feature. Additionally, we employ the Multi-scale Geometry-aware Upsampler module to progressively enhance local details. This is achieved through cross attention between the multi-scale features extracted from the partial input and the features derived from previously estimated points. Extensive experiments on the PCN, ShapeNet-55/34, and KITTI benchmarks demonstrate that our GeoFormer outperforms recent methods, achieving the state-of-the-art performance. Our code is available at \href{https://github.com/Jinpeng-Yu/GeoFormer}{https://github.com/Jinpeng-Yu/GeoFormer}.

Yihao Zhi, Shenhan Qian, Xinhao Yan et al.

Modeling the human body in a canonical space is a common practice for capturing and animation. But when involving the neural radiance field (NeRF), learning a static NeRF in the canonical space is not enough because the lighting of the body changes when the person moves even though the scene lighting is constant. Previous methods alleviate the inconsistency of lighting by learning a per-frame embedding, but this operation does not generalize to unseen poses. Given that the lighting condition is static in the world space while the human body is consistent in the canonical space, we propose a dual-space NeRF that models the scene lighting and the human body with two MLPs in two separate spaces. To bridge these two spaces, previous methods mostly rely on the linear blend skinning (LBS) algorithm. However, the blending weights for LBS of a dynamic neural field are intractable and thus are usually memorized with another MLP, which does not generalize to novel poses. Although it is possible to borrow the blending weights of a parametric mesh such as SMPL, the interpolation operation introduces more artifacts. In this paper, we propose to use the barycentric mapping, which can directly generalize to unseen poses and surprisingly achieves superior results than LBS with neural blending weights. Quantitative and qualitative results on the Human3.6M and the ZJU-MoCap datasets show the effectiveness of our method.

Yuting Xiao, Jingwei Xu, Zehao Yu et al.

In recent years, the neural implicit surface has emerged as a powerful representation for multi-view surface reconstruction due to its simplicity and state-of-the-art performance. However, reconstructing smooth and detailed surfaces in indoor scenes from multi-view images presents unique challenges. Indoor scenes typically contain large texture-less regions, making the photometric loss unreliable for optimizing the implicit surface. Previous work utilizes monocular geometry priors to improve the reconstruction in indoor scenes. However, monocular priors often contain substantial errors in thin structure regions due to domain gaps and the inherent inconsistencies when derived independently from different views. This paper presents \textbf{DebSDF} to address these challenges, focusing on the utilization of uncertainty in monocular priors and the bias in SDF-based volume rendering. We propose an uncertainty modeling technique that associates larger uncertainties with larger errors in the monocular priors. High-uncertainty priors are then excluded from optimization to prevent bias. This uncertainty measure also informs an importance-guided ray sampling and adaptive smoothness regularization, enhancing the learning of fine structures. We further introduce a bias-aware signed distance function to density transformation that takes into account the curvature and the angle between the view direction and the SDF normals to reconstruct fine details better. Our approach has been validated through extensive experiments on several challenging datasets, demonstrating improved qualitative and quantitative results in reconstructing thin structures in indoor scenes, thereby outperforming previous work.

Jiale Xu, Xintao Wang, Yan-Pei Cao et al.

Enhancing AI systems to perform tasks following human instructions can significantly boost productivity. In this paper, we present InstructP2P, an end-to-end framework for 3D shape editing on point clouds, guided by high-level textual instructions. InstructP2P extends the capabilities of existing methods by synergizing the strengths of a text-conditioned point cloud diffusion model, Point-E, and powerful language models, enabling color and geometry editing using language instructions. To train InstructP2P, we introduce a new shape editing dataset, constructed by integrating a shape segmentation dataset, off-the-shelf shape programs, and diverse edit instructions generated by a large language model, ChatGPT. Our proposed method allows for editing both color and geometry of specific regions in a single forward pass, while leaving other regions unaffected. In our experiments, InstructP2P shows generalization capabilities, adapting to novel shape categories and instructions, despite being trained on a limited amount of data.

Shenhan Qian, Jiale Xu, Ziwei Liu et al.

We propose united implicit functions (UNIF), a part-based method for clothed human reconstruction and animation with raw scans and skeletons as the input. Previous part-based methods for human reconstruction rely on ground-truth part labels from SMPL and thus are limited to minimal-clothed humans. In contrast, our method learns to separate parts from body motions instead of part supervision, thus can be extended to clothed humans and other articulated objects. Our Partition-from-Motion is achieved by a bone-centered initialization, a bone limit loss, and a section normal loss that ensure stable part division even when the training poses are limited. We also present a minimal perimeter loss for SDF to suppress extra surfaces and part overlapping. Another core of our method is an adjacent part seaming algorithm that produces non-rigid deformations to maintain the connection between parts which significantly relieves the part-based artifacts. Under this algorithm, we further propose "Competing Parts", a method that defines blending weights by the relative position of a point to bones instead of the absolute position, avoiding the generalization problem of neural implicit functions with inverse LBS (linear blend skinning). We demonstrate the effectiveness of our method by clothed human body reconstruction and animation on the CAPE and the ClothSeq datasets.

Yihao Zhi, Xiaodong Cun, Xuelin Chen et al.

Gestures are non-verbal but important behaviors accompanying people's speech. While previous methods are able to generate speech rhythm-synchronized gestures, the semantic context of the speech is generally lacking in the gesticulations. Although semantic gestures do not occur very regularly in human speech, they are indeed the key for the audience to understand the speech context in a more immersive environment. Hence, we introduce LivelySpeaker, a framework that realizes semantics-aware co-speech gesture generation and offers several control handles. In particular, our method decouples the task into two stages: script-based gesture generation and audio-guided rhythm refinement. Specifically, the script-based gesture generation leverages the pre-trained CLIP text embeddings as the guidance for generating gestures that are highly semantically aligned with the script. Then, we devise a simple but effective diffusion-based gesture generation backbone simply using pure MLPs, that is conditioned on only audio signals and learns to gesticulate with realistic motions. We utilize such powerful prior to rhyme the script-guided gestures with the audio signals, notably in a zero-shot setting. Our novel two-stage generation framework also enables several applications, such as changing the gesticulation style, editing the co-speech gestures via textual prompting, and controlling the semantic awareness and rhythm alignment with guided diffusion. Extensive experiments demonstrate the advantages of the proposed framework over competing methods. In addition, our core diffusion-based generative model also achieves state-of-the-art performance on two benchmarks. The code and model will be released to facilitate future research.

Ye Huang, Di Kang, Shenghua Gao et al.

Existing pyramid-based upsamplers (e.g. SemanticFPN), although efficient, usually produce less accurate results compared to dilation-based models when using the same backbone. This is partially caused by the contaminated high-level features since they are fused and fine-tuned with noisy low-level features on limited data. To address this issue, we propose to use powerful pre-trained high-level features as guidance (HFG) so that the upsampler can produce robust results. Specifically, \emph{only} the high-level features from the backbone are used to train the class tokens, which are then reused by the upsampler for classification, guiding the upsampler features to more discriminative backbone features. One crucial design of the HFG is to protect the high-level features from being contaminated by using proper stop-gradient operations so that the backbone does not update according to the noisy gradient from the upsampler. To push the upper limit of HFG, we introduce a context augmentation encoder (CAE) that can efficiently and effectively operate on the low-resolution high-level feature, resulting in improved representation and thus better guidance. We named our complete solution as the High-Level Features Guided Decoder (HFGD). We evaluate the proposed HFGD on three benchmarks: Pascal Context, COCOStuff164k, and Cityscapes. HFGD achieves state-of-the-art results among methods that do not use extra training data, demonstrating its effectiveness and generalization ability.

Wenqiao Li, Xiaohao Xu, Yao Gu et al.

Recently, 3D anomaly detection, a crucial problem involving fine-grained geometry discrimination, is getting more attention. However, the lack of abundant real 3D anomaly data limits the scalability of current models. To enable scalable anomaly data collection, we propose a 3D anomaly synthesis pipeline to adapt existing large-scale 3Dmodels for 3D anomaly detection. Specifically, we construct a synthetic dataset, i.e., Anomaly-ShapeNet, basedon ShapeNet. Anomaly-ShapeNet consists of 1600 point cloud samples under 40 categories, which provides a rich and varied collection of data, enabling efficient training and enhancing adaptability to industrial scenarios. Meanwhile,to enable scalable representation learning for 3D anomaly localization, we propose a self-supervised method, i.e., Iterative Mask Reconstruction Network (IMRNet). During training, we propose a geometry-aware sample module to preserve potentially anomalous local regions during point cloud down-sampling. Then, we randomly mask out point patches and sent the visible patches to a transformer for reconstruction-based self-supervision. During testing, the point cloud repeatedly goes through the Mask Reconstruction Network, with each iteration's output becoming the next input. By merging and contrasting the final reconstructed point cloud with the initial input, our method successfully locates anomalies. Experiments show that IMRNet outperforms previous state-of-the-art methods, achieving 66.1% in I-AUC on Anomaly-ShapeNet dataset and 72.5% in I-AUC on Real3D-AD dataset. Our dataset will be released at https://github.com/Chopper-233/Anomaly-ShapeNet

Yuting Xiao, Yiqun Zhao, Yanyu Xu et al.

We represent the ResNeRF, a novel geometry-guided two-stage framework for indoor scene novel view synthesis. Be aware of that a good geometry would greatly boost the performance of novel view synthesis, and to avoid the geometry ambiguity issue, we propose to characterize the density distribution of the scene based on a base density estimated from scene geometry and a residual density parameterized by the geometry. In the first stage, we focus on geometry reconstruction based on SDF representation, which would lead to a good geometry surface of the scene and also a sharp density. In the second stage, the residual density is learned based on the SDF learned in the first stage for encoding more details about the appearance. In this way, our method can better learn the density distribution with the geometry prior for high-fidelity novel view synthesis while preserving the 3D structures. Experiments on large-scale indoor scenes with many less-observed and textureless areas show that with the good 3D surface, our method achieves state-of-the-art performance for novel view synthesis.

Jing Li, Jinpeng Yu, Ruoyu Wang et al.

Given only a set of images, neural implicit surface representation has shown its capability in 3D surface reconstruction. However, as the nature of per-scene optimization is based on the volumetric rendering of color, previous neural implicit surface reconstruction methods usually fail in low-textured regions, including the floors, walls, etc., which commonly exist for indoor scenes. Being aware of the fact that these low-textured regions usually correspond to planes, without introducing additional ground-truth supervisory signals or making additional assumptions about the room layout, we propose to leverage a novel Pseudo Plane-regularized Signed Distance Field (P$^2$SDF) for indoor scene reconstruction. Specifically, we consider adjacent pixels with similar colors to be on the same pseudo planes. The plane parameters are then estimated on the fly during training by an efficient and effective two-step scheme. Then the signed distances of the points on the planes are regularized by the estimated plane parameters in the training phase. As the unsupervised plane segments are usually noisy and inaccurate, we propose to assign different weights to the sampled points on the plane in plane estimation as well as the regularization loss. The weights come by fusing the plane segments from different views. As the sampled rays in the planar regions are redundant, leading to inefficient training, we further propose a keypoint-guided rays sampling strategy that attends to the informative textured regions with large color variations, and the implicit network gets a better reconstruction, compared with the original uniform ray sampling strategy. Experiments show that our P$^2$SDF achieves competitive reconstruction performance in Manhattan scenes. Further, as we do not introduce any additional room layout assumption, our P$^2$SDF generalizes well to the reconstruction of non-Manhattan scenes.

Binbin Huang, Xingyue Peng, Siyuan Shen et al.

We introduce Omni-LOS, a neural computational imaging method for conducting holistic shape reconstruction (HSR) of complex objects utilizing a Single-Photon Avalanche Diode (SPAD)-based time-of-flight sensor. As illustrated in Fig. 1, our method enables new capabilities to reconstruct near-$360^\circ$ surrounding geometry of an object from a single scan spot. In such a scenario, traditional line-of-sight (LOS) imaging methods only see the front part of the object and typically fail to recover the occluded back regions. Inspired by recent advances of non-line-of-sight (NLOS) imaging techniques which have demonstrated great power to reconstruct occluded objects, Omni-LOS marries LOS and NLOS together, leveraging their complementary advantages to jointly recover the holistic shape of the object from a single scan position. The core of our method is to put the object nearby diffuse walls and augment the LOS scan in the front view with the NLOS scans from the surrounding walls, which serve as virtual ``mirrors'' to trap lights toward the object. Instead of separately recovering the LOS and NLOS signals, we adopt an implicit neural network to represent the object, analogous to NeRF and NeTF. While transients are measured along straight rays in LOS but over the spherical wavefronts in NLOS, we derive differentiable ray propagation models to simultaneously model both types of transient measurements so that the NLOS reconstruction also takes into account the direct LOS measurements and vice versa. We further develop a proof-of-concept Omni-LOS hardware prototype for real-world validation. Comprehensive experiments on various wall settings demonstrate that Omni-LOS successfully resolves shape ambiguities caused by occlusions, achieves high-fidelity 3D scan quality, and manages to recover objects of various scales and complexity.

Shuang Chen, Kaituo Feng, Hangting Chen et al.

Deep search has become a crucial capability for frontier multimodal agents, enabling models to solve complex questions through active search, evidence verification, and multi-step reasoning. Despite rapid progress, top-tier multimodal search agents remain difficult to reproduce, largely due to the absence of open high-quality training data, transparent trajectory synthesis pipelines, or detailed training recipes. To this end, we introduce OpenSearch-VL, a fully open-source recipe for training frontier multimodal deep search agents with agentic reinforcement learning. First, we curated a dedicated pipeline to construct high-quality training data through Wikipedia path sampling, fuzzy entity rewriting, and source-anchor visual grounding, which jointly reduce shortcuts and one-step retrieval collapse. Based on this pipeline, we curate two training datasets, SearchVL-SFT-36k for SFT and SearchVL-RL-8k for RL. Besides, we design a diverse tool environment that unifies text search, image search, OCR, cropping, sharpening, super-resolution, and perspective correction, enabling agents to combine active perception with external knowledge acquisition. Finally, we propose a multi-turn fatal-aware GRPO training algorithm that handles cascading tool failures by masking post-failure tokens while preserving useful pre-failure reasoning through one-sided advantage clamping. Built on this recipe, OpenSearch-VL delivers substantial performance gains, with over 10-point average improvements across seven benchmarks, and achieves results comparable to proprietary commercial models on several tasks. We will release all data, code, and models to support open research on multimodal deep search agents.

Xinwu Ye, He Cao, Hao Li et al.

Biomolecular generators are often adapted with reward feedback to improve task-specific utility, but pushing utility alone can concentrate generation on a narrow family of candidates. Maintaining diversity is difficult because sample diversity is a set-level property. We introduce Supergroup Relative Policy Optimization (SGRPO), a flexible GRPO-style framework that directly constructs rewards from set-level diversity. For each condition, SGRPO samples a supergroup of candidate sets, compares their diversity under the same condition, and redistributes the group diversity reward to individual rollouts through leave-one-out diversity contributions before combining it with rollout-level utility. This design decouples SGRPO from a particular generator, utility reward, or diversity metric, and allows instantiation with different GRPO-style approaches. We evaluate SGRPO on de novo small-molecule design, pocket-based small-molecule design, and de novo protein design, instantiating it with both GRPO and Coupled-GRPO across autoregressive and discrete diffusion generators. Across decoding sweeps, SGRPO expands the utility-diversity Pareto frontier and achieves the best frontier-level metrics relative to pretrained generators, GRPO, and memory-assisted GRPO when applicable. Our analyses further show that direct set-level diversity rewards remain effective with small groups and help preserve broader generation-distribution coverage during post-training. The code is available at https://github.com/IDEA-XL/SGRPO.

Yiqun Zhao, Chenming Wu, Binbin Huang et al.

Efficient and accurate reconstruction of a relightable, dynamic clothed human avatar from a monocular video is crucial for the entertainment industry. This paper presents SGIA (Surfel-based Gaussian Inverse Avatar), which introduces efficient training and rendering for relightable dynamic human reconstruction. SGIA advances previous Gaussian Avatar methods by comprehensively modeling Physically-Based Rendering (PBR) properties for clothed human avatars, allowing for the manipulation of avatars into novel poses under diverse lighting conditions. Specifically, our approach integrates pre-integration and image-based lighting for fast light calculations that surpass the performance of existing implicit-based techniques. To address challenges related to material lighting disentanglement and accurate geometry reconstruction, we propose an innovative occlusion approximation strategy and a progressive training approach. Extensive experiments demonstrate that SGIA not only achieves highly accurate physical properties but also significantly enhances the realistic relighting of dynamic human avatars, providing a substantial speed advantage. We exhibit more results in our project page: https://GS-IA.github.io.

Dacheng Qi, Chenyu Wang, Jingwei Xu et al.

Constructing computer-aided design (CAD) models is labor-intensive but essential for engineering and manufacturing. Recent advances in Large Language Models (LLMs) have inspired the LLM-based CAD generation by representing CAD as command sequences. But these methods struggle in practical scenarios because command sequence representation does not support entity selection (e.g. faces or edges), limiting its ability to support complex editing operations such as chamfer or fillet. Further, the discretization of a continuous variable during sketch and extrude operations may result in topological errors. To address these limitations, we present Pointer-CAD, a novel LLM-based CAD generation framework that leverages a pointer-based command sequence representation to explicitly incorporate the geometric information of B-rep models into sequential modeling. In particular, Pointer-CAD decomposes CAD model generation into steps, conditioning the generation of each subsequent step on both the textual description and the B-rep generated from previous steps. Whenever an operation requires the selection of a specific geometric entity, the LLM predicts a Pointer that selects the most feature-consistent candidate from the available set. Such a selection operation also reduces the quantization error in the command sequence-based representation. To support the training of Pointer-CAD, we develop a data annotation pipeline that produces expert-level natural language descriptions and apply it to build a dataset of approximately 575K CAD models. Extensive experimental results demonstrate that Pointer-CAD effectively supports the generation of complex geometric structures and reduces segmentation error to an extremely low level, achieving a significant improvement over prior command sequence methods, thereby significantly mitigating the topological inaccuracies introduced by quantization error.

Hongye Zeng, kang Zhou, Songhan Ge et al.

Three-dimensional (3D) ultrasound imaging technique has been applied for scoliosis assessment, but current assessment method only uses coronal projection image and cannot illustrate the 3D deformity and vertebra rotation. The vertebra detection is essential to reveal 3D spine information, but the detection task is challenging due to complex data and limited annotations. We propose VertMatch, a two-step framework to detect vertebral structures in 3D ultrasound volume by utilizing unlabeled data in semi-supervised manner. The first step is to detect the possible positions of structures on transverse slice globally, and then the local patches are cropped based on detected positions. The second step is to distinguish whether the patches contain real vertebral structures and screen the predicted positions from the first step. VertMatch develops three novel components for semi-supervised learning: for position detection in the first step, (1) anatomical prior is used to screen pseudo labels generated from confidence threshold method; (2) multi-slice consistency is used to utilize more unlabeled data by inputting multiple adjacent slices; (3) for patch identification in the second step, the categories are rebalanced in each batch to solve imbalance problem. Experimental results demonstrate that VertMatch can detect vertebra accurately in ultrasound volume and outperforms state-of-the-art methods. VertMatch is also validated in clinical application on forty ultrasound scans, and it can be a promising approach for 3D assessment of scoliosis.

Shuo Wang, Binbin Huang, Ruoyu Wang et al.

Previous surface reconstruction methods either suffer from low geometric accuracy or lengthy training times when dealing with real-world complex dynamic scenes involving multi-person activities, and human-object interactions. To tackle the dynamic contents and the occlusions in complex scenes, we present a space-time 2D Gaussian Splatting approach. Specifically, to improve geometric quality in dynamic scenes, we learn canonical 2D Gaussian splats and deform these 2D Gaussian splats while enforcing the disks of the Gaussian located on the surface of the objects by introducing depth and normal regularizers. Further, to tackle the occlusion issues in complex scenes, we introduce a compositional opacity deformation strategy, which further reduces the surface recovery of those occluded areas. Experiments on real-world sparse-view video datasets and monocular dynamic datasets demonstrate that our reconstructions outperform state-of-the-art methods, especially for the surface of the details. The project page and more visualizations can be found at: https://tb2-sy.github.io/st-2dgs/.

Yiqun Zhao, Zibo Zhao, Jing Li et al.

Indoor scene generation aims at creating shape-compatible, style-consistent furniture arrangements within a spatially reasonable layout. However, most existing approaches primarily focus on generating plausible furniture layouts without incorporating specific details related to individual furniture pieces. To address this limitation, we propose a two-stage model integrating shape priors into the indoor scene generation by encoding furniture as anchor latent representations. In the first stage, we employ discrete vector quantization to encode furniture pieces as anchor-latents. Based on the anchor-latents representation, the shape and location information of the furniture was characterized by a concatenation of location, size, orientation, class, and our anchor latent. In the second stage, we leverage a transformer model to predict indoor scenes autoregressively. Thanks to incorporating the proposed anchor-latents representations, our generative model produces shape-compatible and style-consistent furniture arrangements and synthesis furniture in diverse shapes. Furthermore, our method facilitates various human interaction applications, such as style-consistent scene completion, object mismatch correction, and controllable object-level editing. Experimental results on the 3D-Front dataset demonstrate that our approach can generate more consistent and compatible indoor scenes compared to existing methods, even without shape retrieval. Additionally, extensive ablation studies confirm the effectiveness of our design choices in the indoor scene generation model.

Feng Chen, Tianzhe Chu, Li Sun et al.

Evaluating embodied systems on real dexterous hardware requires more than isolated primitive skills: an agent must perceive a changing tabletop scene, choose a context-appropriate action, execute it with a dexterous hand, and leave the scene usable for later decisions. We introduce DexHoldem, a real-world system-level benchmark built around Texas Hold'em dexterous manipulation with a ShadowHand. DexHoldem provides 1,470 teleoperated demonstrations across 14 Texas Hold'em manipulation primitives, a standardized physical policy benchmark, and an agentic perception benchmark that tests whether agents can recover the structured game state needed for embodied decision making. On primitive execution, $π_{0.5}$ obtains the highest task completion rate ($61.2\%$), while $π_{0.5}$ and $π_0$ tie on scene-preserving success rate ($47.5\%$). On agentic perception, Opus 4.7 obtains the best strict problem-level accuracy ($34.3\%$), while GPT 5.5 obtains the best average field-wise accuracy ($66.8\%$), exposing a gap between isolated visual sub-capabilities and complete routing-relevant state recovery. Finally, we instantiate the full embodied-agent loop in three case studies, where waiting, recovery dispatches, human-help requests, and repeated primitive execution reveal how perception and policy errors accumulate during closed-loop deployment. DexHoldem therefore evaluates dexterous tabletop execution, agentic perception, and embodied decision routing in a shared physical setting. Project page: https://dexholdem.github.io/Dexholdem/.

Binbin Huang, Zehao Yu, Anpei Chen et al.

3D Gaussian Splatting (3DGS) has recently revolutionized radiance field reconstruction, achieving high quality novel view synthesis and fast rendering speed without baking. However, 3DGS fails to accurately represent surfaces due to the multi-view inconsistent nature of 3D Gaussians. We present 2D Gaussian Splatting (2DGS), a novel approach to model and reconstruct geometrically accurate radiance fields from multi-view images. Our key idea is to collapse the 3D volume into a set of 2D oriented planar Gaussian disks. Unlike 3D Gaussians, 2D Gaussians provide view-consistent geometry while modeling surfaces intrinsically. To accurately recover thin surfaces and achieve stable optimization, we introduce a perspective-correct 2D splatting process utilizing ray-splat intersection and rasterization. Additionally, we incorporate depth distortion and normal consistency terms to further enhance the quality of the reconstructions. We demonstrate that our differentiable renderer allows for noise-free and detailed geometry reconstruction while maintaining competitive appearance quality, fast training speed, and real-time rendering.

Xinwu Ye, Yicheng Mao, Jia Zhang et al.

Chemical large language models (LLMs) predominantly rely on explicit Chain-of-Thought (CoT) in natural language to perform complex reasoning. However, chemical reasoning is inherently continuous and structural, and forcing it into discrete linguistic tokens introduces a fundamental representation mismatch that constrains both efficiency and performance. We introduce LatentChem, a latent reasoning interface that decouples chemical computation from textual generation, enabling models to perform multi-step reasoning directly in continuous latent space while emitting language only for final outputs. Remarkably, we observe a consistent emergent behavior: when optimized solely for task success, models spontaneously internalize reasoning, progressively abandoning verbose textual derivations in favor of implicit latent computation. This shift is not merely stylistic but computationally advantageous. Across diverse chemical reasoning benchmarks, LatentChem achieves a 59.88\% non-tie win rate over strong CoT-based baselines on ChemCoTBench, while delivering a 10.84$\times$ average inference speedup. Our results provide empirical evidence that chemical reasoning is more naturally and effectively realized as continuous latent dynamics rather than discretized linguistic trajectories.

Jiale Xu, Weihao Cheng, Yiming Gao et al.

We present InstantMesh, a feed-forward framework for instant 3D mesh generation from a single image, featuring state-of-the-art generation quality and significant training scalability. By synergizing the strengths of an off-the-shelf multiview diffusion model and a sparse-view reconstruction model based on the LRM architecture, InstantMesh is able to create diverse 3D assets within 10 seconds. To enhance the training efficiency and exploit more geometric supervisions, e.g, depths and normals, we integrate a differentiable iso-surface extraction module into our framework and directly optimize on the mesh representation. Experimental results on public datasets demonstrate that InstantMesh significantly outperforms other latest image-to-3D baselines, both qualitatively and quantitatively. We release all the code, weights, and demo of InstantMesh, with the intention that it can make substantial contributions to the community of 3D generative AI and empower both researchers and content creators.

Qingchuan Zhang, He Cao, Hao Li et al.

Molecular optimization seeks to improve a molecule through small structural edits while preserving similarity to the starting compound. Recent language-model approaches typically treat this task as prompt-conditioned sequence generation. However, relying on natural language introduces an inherent data-scaling bottleneck, often leads to chemical hallucinations, and ignores the strong context dependence of fragment effects. We present FORGE, a two-stage framework that reformulates molecular optimization as context-aware local editing. By utilizing automatically mined, verified low-to-high edit pairs instead of expensive human text annotations, Stage 1 ranks candidate fragments by their property contribution under the full molecular context to inject chemical prior, and Stage 2 generates explicit fragment replacements. Built on a compact 0.6B language model, FORGE further adapts to unseen black-box objectives through in-context demonstrations. Across Prompt-MolOpt, PMO-1k and ChemCoTBench, FORGE consistently outperforms prior methods, including substantially larger language models and graph methods. These results highlight the value of explicit fragment-level supervision as a more easily obtainable, scalable, and hallucination-less alternative to natural language training.

Feng Chen, Zhuxiu Xu, Tianzhe Chu et al.

Data scarcity remains a fundamental bottleneck for embodied intelligence. Existing approaches use large language models (LLMs) to automate gripper-based simulation generation, but they transfer poorly to dexterous manipulation, which demands more specialized environment design. Meanwhile, dexterous manipulation tasks are inherently more difficult due to their higher degrees of freedom. Massively generating feasible and trainable dexterous hand tasks remains an open challenge. To this end, we present GenDexHand, a generative simulation pipeline that autonomously produces diverse robotic tasks and environments for dexterous manipulation. GenDexHand introduces a closed-loop refinement process that adjusts object placements and scales based on vision-language model (VLM) feedback, substantially improving the average quality of generated environments. Each task is further decomposed into sub-tasks to enable sequential reinforcement learning, reducing training time and increasing success rates. Our work provides a viable path toward scalable training of diverse dexterous hand behaviors in embodied intelligence by offering a simulation-based solution to synthetic data generation. Our website: https://winniechen2002.github.io/GenDexHand/.

Ruoyu Wang, Yi Ma, Shenghua Gao

Currently almost all state-of-the-art novel view synthesis and reconstruction models rely on calibrated cameras or additional geometric priors for training. These prerequisites significantly limit their applicability to massive uncalibrated data. To alleviate this requirement and unlock the potential for self-supervised training on large-scale uncalibrated videos, we propose a novel two-stage strategy to train a view synthesis model from only raw video frames or multi-view images, without providing camera parameters or other priors. In the first stage, we learn to reconstruct the scene implicitly in a latent space without relying on any explicit 3D representation. Specifically, we predict per-frame latent camera and scene context features, and employ a view synthesis model as a proxy for explicit rendering. This pretraining stage substantially reduces the optimization complexity and encourages the network to learn the underlying 3D consistency in a self-supervised manner. The learned latent camera and implicit scene representation have a large gap compared with the real 3D world. To reduce this gap, we introduce the second stage training by explicitly predicting 3D Gaussian primitives. We additionally apply explicit Gaussian Splatting rendering loss and depth projection loss to align the learned latent representations with physically grounded 3D geometry. In this way, Stage 1 provides a strong initialization and Stage 2 enforces 3D consistency - the two stages are complementary and mutually beneficial. Extensive experiments demonstrate the effectiveness of our approach, achieving high-quality novel view synthesis and accurate camera pose estimation, compared to methods that employ supervision with calibration, pose, or depth information. The code is available at https://github.com/Dwawayu/Pensieve.

Chenyu Wang, Weixin Luo, Sixun Dong et al.

Recently, the astonishing performance of large language models (LLMs) in natural language comprehension and generation tasks triggered lots of exploration of using them as central controllers to build agent systems. Multiple studies focus on bridging the LLMs to external tools to extend the application scenarios. However, the current LLMs' ability to perceive tool use is limited to a single text query, which may result in ambiguity in understanding the users' real intentions. LLMs are expected to eliminate that by perceiving the information in the visual- or auditory-grounded instructions. Therefore, in this paper, we propose MLLM-Tool, a system incorporating open-source LLMs and multi-modal encoders so that the learned LLMs can be conscious of multi-modal input instruction and then select the function-matched tool correctly. To facilitate the evaluation of the model's capability, we collect a dataset featuring multi-modal input tools from HuggingFace. Another essential feature of our dataset is that it also contains multiple potential choices for the same instruction due to the existence of identical functions and synonymous functions, which provides more potential solutions for the same query. The experiments reveal that our MLLM-Tool is capable of recommending appropriate tools for multi-modal instructions. Codes and data are available at https://github.com/MLLM-Tool/MLLM-Tool.

Wei Zhou, Xiangyu Zhang, Hongyu Wang et al.

In this paper, we propose a method to add constraints that are un-formulatable in generative adversarial networks (GAN)-based arbitrary size RAW Bayer image generation. It is shown theoretically that by using the transformed data in GAN training, it is able to improve the learning of the original data distribution, owing to the invariant of Jensen-Shannon (JS) divergence between two distributions under invertible and differentiable transformation. Benefiting from the proposed method, RAW Bayer pattern images can be generated by configuring the transformation as demosaicing. It is shown that by adding another transformation, the proposed method is able to synthesize high-quality RAW Bayer images with arbitrary size. Experimental results show that images generated by the proposed method outperform the existing methods in the Fréchet inception distance (FID) score, peak signal to noise ratio (PSNR), and mean structural similarity (MSSIM), and the training process is more stable. To the best knowledge of the authors, there is no open-source, large-scale image dataset in the RAW Bayer domain, which is crucial for research works aiming to explore the image signal processing (ISP) pipeline design for computer vision tasks. Converting the existing commonly used color image datasets to their corresponding RAW Bayer versions, the proposed method can be a promising solution to the RAW image dataset problem. We also show in the experiments that, by training object detection frameworks using the synthesized RAW Bayer images, they can be used in an end-to-end manner (from RAW images to vision tasks) with negligible performance degradation.

Yepeng Liu, Zaiwang Gu, Shenghua Gao et al.

With the emergence of service robots and surveillance cameras, dynamic face recognition (DFR) in wild has received much attention in recent years. Face detection and head pose estimation are two important steps for DFR. Very often, the pose is estimated after the face detection. However, such sequential computations lead to higher latency. In this paper, we propose a low latency and lightweight network for simultaneous face detection, landmark localization and head pose estimation. Inspired by the observation that it is more challenging to locate the facial landmarks for faces with large angles, a pose loss is proposed to constrain the learning. Moreover, we also propose an uncertainty multi-task loss to learn the weights of individual tasks automatically. Another challenge is that robots often use low computational units like ARM based computing core and we often need to use lightweight networks instead of the heavy ones, which lead to performance drop especially for small and hard faces. In this paper, we propose online feedback sampling to augment the training samples across different scales, which increases the diversity of training data automatically. Through validation in commonly used WIDER FACE, AFLW and AFLW2000 datasets, the results show that the proposed method achieves the state-of-the-art performance in low computational resources. The code and data will be available at https://github.com/lyp-deeplearning/MOS-Multi-Task-Face-Detect.

Dongze Lian, Zehao Yu, Xing Sun et al.

An Axial Shifted MLP architecture (AS-MLP) is proposed in this paper. Different from MLP-Mixer, where the global spatial feature is encoded for information flow through matrix transposition and one token-mixing MLP, we pay more attention to the local features interaction. By axially shifting channels of the feature map, AS-MLP is able to obtain the information flow from different axial directions, which captures the local dependencies. Such an operation enables us to utilize a pure MLP architecture to achieve the same local receptive field as CNN-like architecture. We can also design the receptive field size and dilation of blocks of AS-MLP, etc, in the same spirit of convolutional neural networks. With the proposed AS-MLP architecture, our model obtains 83.3% Top-1 accuracy with 88M parameters and 15.2 GFLOPs on the ImageNet-1K dataset. Such a simple yet effective architecture outperforms all MLP-based architectures and achieves competitive performance compared to the transformer-based architectures (e.g., Swin Transformer) even with slightly lower FLOPs. In addition, AS-MLP is also the first MLP-based architecture to be applied to the downstream tasks (e.g., object detection and semantic segmentation). The experimental results are also impressive. Our proposed AS-MLP obtains 51.5 mAP on the COCO validation set and 49.5 MS mIoU on the ADE20K dataset, which is competitive compared to the transformer-based architectures. Our AS-MLP establishes a strong baseline of MLP-based architecture. Code is available at https://github.com/svip-lab/AS-MLP.

Jiale Xu, Jia Zheng, Yanyu Xu et al.

Existing view synthesis methods mainly focus on the perspective images and have shown promising results. However, due to the limited field-of-view of the pinhole camera, the performance quickly degrades when large camera movements are adopted. In this paper, we make the first attempt to generate novel views from a single indoor panorama and take the large camera translations into consideration. To tackle this challenging problem, we first use Convolutional Neural Networks (CNNs) to extract the deep features and estimate the depth map from the source-view image. Then, we leverage the room layout prior, a strong structural constraint of the indoor scene, to guide the generation of target views. More concretely, we estimate the room layout in the source view and transform it into the target viewpoint as guidance. Meanwhile, we also constrain the room layout of the generated target-view images to enforce geometric consistency. To validate the effectiveness of our method, we further build a large-scale photo-realistic dataset containing both small and large camera translations. The experimental results on our challenging dataset demonstrate that our method achieves state-of-the-art performance. The project page is at https://github.com/bluestyle97/PNVS.

Zhaoyuan Yin, Jia Zheng, Weixin Luo et al.

This paper proposes a framework for the interactive video object segmentation (VOS) in the wild where users can choose some frames for annotations iteratively. Then, based on the user annotations, a segmentation algorithm refines the masks. The previous interactive VOS paradigm selects the frame with some worst evaluation metric, and the ground truth is required for calculating the evaluation metric, which is impractical in the testing phase. In contrast, in this paper, we advocate that the frame with the worst evaluation metric may not be exactly the most valuable frame that leads to the most performance improvement across the video. Thus, we formulate the frame selection problem in the interactive VOS as a Markov Decision Process, where an agent is learned to recommend the frame under a deep reinforcement learning framework. The learned agent can automatically determine the most valuable frame, making the interactive setting more practical in the wild. Experimental results on the public datasets show the effectiveness of our learned agent without any changes to the underlying VOS algorithms. Our data, code, and models are available at https://github.com/svip-lab/IVOS-W.

Zehao Yu, Lei Jin, Shenghua Gao

This paper tackles the unsupervised depth estimation task in indoor environments. The task is extremely challenging because of the vast areas of non-texture regions in these scenes. These areas could overwhelm the optimization process in the commonly used unsupervised depth estimation framework proposed for outdoor environments. However, even when those regions are masked out, the performance is still unsatisfactory. In this paper, we argue that the poor performance suffers from the non-discriminative point-based matching. To this end, we propose P$^2$Net. We first extract points with large local gradients and adopt patches centered at each point as its representation. Multiview consistency loss is then defined over patches. This operation significantly improves the robustness of the network training. Furthermore, because those textureless regions in indoor scenes (e.g., wall, floor, roof, \etc) usually correspond to planar regions, we propose to leverage superpixels as a plane prior. We enforce the predicted depth to be well fitted by a plane within each superpixel. Extensive experiments on NYUv2 and ScanNet show that our P$^2$Net outperforms existing approaches by a large margin. Code is available at \url{https://github.com/svip-lab/Indoor-SfMLearner}.

Kun Huang, Yifan Wang, Zihan Zhou et al.

In this paper, we propose a learning-based approach to the task of automatically extracting a "wireframe" representation for images of cluttered man-made environments. The wireframe (see Fig. 1) contains all salient straight lines and their junctions of the scene that encode efficiently and accurately large-scale geometry and object shapes. To this end, we have built a very large new dataset of over 5,000 images with wireframes thoroughly labelled by humans. We have proposed two convolutional neural networks that are suitable for extracting junctions and lines with large spatial support, respectively. The networks trained on our dataset have achieved significantly better performance than state-of-the-art methods for junction detection and line segment detection, respectively. We have conducted extensive experiments to evaluate quantitatively and qualitatively the wireframes obtained by our method, and have convincingly shown that effectively and efficiently parsing wireframes for images of man-made environments is a feasible goal within reach. Such wireframes could benefit many important visual tasks such as feature correspondence, 3D reconstruction, vision-based mapping, localization, and navigation. The data and source code are available at https://github.com/huangkuns/wireframe.

Zehao Yu, Shenghua Gao

Almost all previous deep learning-based multi-view stereo (MVS) approaches focus on improving reconstruction quality. Besides quality, efficiency is also a desirable feature for MVS in real scenarios. Towards this end, this paper presents a Fast-MVSNet, a novel sparse-to-dense coarse-to-fine framework, for fast and accurate depth estimation in MVS. Specifically, in our Fast-MVSNet, we first construct a sparse cost volume for learning a sparse and high-resolution depth map. Then we leverage a small-scale convolutional neural network to encode the depth dependencies for pixels within a local region to densify the sparse high-resolution depth map. At last, a simple but efficient Gauss-Newton layer is proposed to further optimize the depth map. On one hand, the high-resolution depth map, the data-adaptive propagation method and the Gauss-Newton layer jointly guarantee the effectiveness of our method. On the other hand, all modules in our Fast-MVSNet are lightweight and thus guarantee the efficiency of our approach. Besides, our approach is also memory-friendly because of the sparse depth representation. Extensive experimental results show that our method is 5$\times$ and 14$\times$ faster than Point-MVSNet and R-MVSNet, respectively, while achieving comparable or even better results on the challenging Tanks and Temples dataset as well as the DTU dataset. Code is available at https://github.com/svip-lab/FastMVSNet.

Dongze Lian, Zehao Yu, Shenghua Gao

By borrowing the wisdom of human in gaze following, we propose a two-stage solution for gaze point prediction of the target persons in a scene. Specifically, in the first stage, both head image and its position are fed into a gaze direction pathway to predict the gaze direction, and then multi-scale gaze direction fields are generated to characterize the distribution of gaze points without considering the scene contents. In the second stage, the multi-scale gaze direction fields are concatenated with the image contents and fed into a heatmap pathway for heatmap regression. There are two merits for our two-stage solution based gaze following: i) our solution mimics the behavior of human in gaze following, therefore it is more psychological plausible; ii) besides using heatmap to supervise the output of our network, we can also leverage gaze direction to facilitate the training of gaze direction pathway, therefore our network can be more robustly trained. Considering that existing gaze following dataset is annotated by the third-view persons, we build a video gaze following dataset, where the ground truth is annotated by the observers in the videos. Therefore it is more reliable. The evaluation with such a dataset reflects the capacity of different methods in real scenarios better. Extensive experiments on both datasets show that our method significantly outperforms existing methods, which validates the effectiveness of our solution for gaze following. Our dataset and codes are released in https://github.com/svip-lab/GazeFollowing.

Ziheng Zhang, Zhengxin Li, Ning Bi et al.

In this paper, we present a novel framework to detect line segments in man-made environments. Specifically, we propose to describe junctions, line segments and relationships between them with a simple graph, which is more structured and informative than end-point representation used in existing line segment detection methods. In order to extract a line segment graph from an image, we further introduce the PPGNet, a convolutional neural network that directly infers a graph from an image. We evaluate our method on published benchmarks including York Urban and Wireframe datasets. The results demonstrate that our method achieves satisfactory performance and generalizes well on all the benchmarks. The source code of our work is available at \url{https://github.com/svip-lab/PPGNet}.

Zehao Yu, Jia Zheng, Dongze Lian et al.

Single-image piece-wise planar 3D reconstruction aims to simultaneously segment plane instances and recover 3D plane parameters from an image. Most recent approaches leverage convolutional neural networks (CNNs) and achieve promising results. However, these methods are limited to detecting a fixed number of planes with certain learned order. To tackle this problem, we propose a novel two-stage method based on associative embedding, inspired by its recent success in instance segmentation. In the first stage, we train a CNN to map each pixel to an embedding space where pixels from the same plane instance have similar embeddings. Then, the plane instances are obtained by grouping the embedding vectors in planar regions via an efficient mean shift clustering algorithm. In the second stage, we estimate the parameter for each plane instance by considering both pixel-level and instance-level consistencies. With the proposed method, we are able to detect an arbitrary number of planes. Extensive experiments on public datasets validate the effectiveness and efficiency of our method. Furthermore, our method runs at 30 fps at the testing time, thus could facilitate many real-time applications such as visual SLAM and human-robot interaction. Code is available at https://github.com/svip-lab/PlanarReconstruction.

Haohan Weng, Zibo Zhao, Biwen Lei et al.

We propose a compressive yet effective mesh representation, Blocked and Patchified Tokenization (BPT), facilitating the generation of meshes exceeding 8k faces. BPT compresses mesh sequences by employing block-wise indexing and patch aggregation, reducing their length by approximately 75\% compared to the original sequences. This compression milestone unlocks the potential to utilize mesh data with significantly more faces, thereby enhancing detail richness and improving generation robustness. Empowered with the BPT, we have built a foundation mesh generative model training on scaled mesh data to support flexible control for point clouds and images. Our model demonstrates the capability to generate meshes with intricate details and accurate topology, achieving SoTA performance on mesh generation and reaching the level for direct product usage.

Jingwei Xu, Chenyu Wang, Zibo Zhao et al.

This paper aims to design a unified Computer-Aided Design (CAD) generation system that can easily generate CAD models based on the user's inputs in the form of textual description, images, point clouds, or even a combination of them. Towards this goal, we introduce the CAD-MLLM, the first system capable of generating parametric CAD models conditioned on the multimodal input. Specifically, within the CAD-MLLM framework, we leverage the command sequences of CAD models and then employ advanced large language models (LLMs) to align the feature space across these diverse multi-modalities data and CAD models' vectorized representations. To facilitate the model training, we design a comprehensive data construction and annotation pipeline that equips each CAD model with corresponding multimodal data. Our resulting dataset, named Omni-CAD, is the first multimodal CAD dataset that contains textual description, multi-view images, points, and command sequence for each CAD model. It contains approximately 450K instances and their CAD construction sequences. To thoroughly evaluate the quality of our generated CAD models, we go beyond current evaluation metrics that focus on reconstruction quality by introducing additional metrics that assess topology quality and surface enclosure extent. Extensive experimental results demonstrate that CAD-MLLM significantly outperforms existing conditional generative methods and remains highly robust to noises and missing points. The project page and more visualizations can be found at: https://cad-mllm.github.io/