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}.

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.

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.

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.

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.

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.

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.

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.

Jiale Xu, Shenghua Gao, Ying Shan

Sparse-view reconstruction models typically require precise camera poses, yet obtaining these parameters from sparse-view images remains challenging. We introduce FreeSplatter, a scalable feed-forward framework that generates high-quality 3D Gaussians from uncalibrated sparse-view images while estimating camera parameters within seconds. Our approach employs a streamlined transformer architecture where self-attention blocks facilitate information exchange among multi-view image tokens, decoding them into pixel-aligned 3D Gaussian primitives within a unified reference frame. This representation enables both high-fidelity 3D modeling and efficient camera parameter estimation using off-the-shelf solvers. We develop two specialized variants--for object-centric and scene-level reconstruction--trained on comprehensive datasets. Remarkably, FreeSplatter outperforms several pose-dependent Large Reconstruction Models (LRMs) by a notable margin while achieving comparable or even better pose estimation accuracy compared to state-of-the-art pose-free reconstruction approach MASt3R in challenging benchmarks. Beyond technical benchmarks, FreeSplatter streamlines text/image-to-3D content creation pipelines, eliminating the complexity of camera pose management while delivering exceptional visual fidelity.

Hongrui Cai, Yuting Xiao, Xuan Wang et al.

We introduce a novel approach to creating ultra-realistic head avatars and rendering them in real-time (>30fps at $2048 \times 1334$ resolution). First, we propose a hybrid explicit representation that combines the advantages of two primitive-based efficient rendering techniques. UV-mapped 3D mesh is utilized to capture sharp and rich textures on smooth surfaces, while 3D Gaussian Splatting is employed to represent complex geometric structures. In the pipeline of modeling an avatar, after tracking parametric models based on captured multi-view RGB videos, our goal is to simultaneously optimize the texture and opacity map of mesh, as well as a set of 3D Gaussian splats localized and rigged onto the mesh facets. Specifically, we perform $α$-blending on the color and opacity values based on the merged and re-ordered z-buffer from the rasterization results of mesh and 3DGS. This process involves the mesh and 3DGS adaptively fitting the captured visual information to outline a high-fidelity digital avatar. To avoid artifacts caused by Gaussian splats crossing the mesh facets, we design a stable hybrid depth sorting strategy. Experiments illustrate that our modeled results exceed those of state-of-the-art approaches.

Guichen Huang, Ruoyu Wang, Xiangjun Gao et al.

3D Gaussian Splatting achieves high-fidelity novel view synthesis, but its application to online long-sequence scenarios is still limited. Existing methods either rely on slow per-scene optimization or fail to provide efficient incremental updates, hindering continuous performance. In this paper, we propose LongSplat, an online real-time 3D Gaussian reconstruction framework designed for long-sequence image input. The core idea is a streaming update mechanism that incrementally integrates current-view observations while selectively compressing redundant historical Gaussians. Crucial to this mechanism is our Gaussian-Image Representation (GIR), a representation that encodes 3D Gaussian parameters into a structured, image-like 2D format. GIR simultaneously enables efficient fusion of current-view and historical Gaussians and identity-aware redundancy compression. These functions enable online reconstruction and adapt the model to long sequences without overwhelming memory or computational costs. Furthermore, we leverage an existing image compression method to guide the generation of more compact and higher-quality 3D Gaussians. Extensive evaluations demonstrate that LongSplat achieves state-of-the-art efficiency-quality trade-offs in real-time novel view synthesis, delivering real-time reconstruction while reducing Gaussian counts by 44\% compared to existing per-pixel Gaussian prediction methods.

Jiada Lu, WeiWei Zhou, Xiang Qian et al.

Repetitive action counting quantifies the frequency of specific actions performed by individuals. However, existing action-counting datasets have limited action diversity, potentially hampering model performance on unseen actions. To address this issue, we propose a framework called First Cycle Annotated Repetitive Action Counting (FCA-RAC). This framework contains 4 parts: 1) a labeling technique that annotates each training video with the start and end of the first action cycle, along with the total action count. This technique enables the model to capture the correlation between the initial action cycle and subsequent actions; 2) an adaptive sampling strategy that maximizes action information retention by adjusting to the speed of the first annotated action cycle in videos; 3) a Multi-Temporal Granularity Convolution (MTGC) module, that leverages the muli-scale first action as a kernel to convolve across the entire video. This enables the model to capture action variations at different time scales within the video; 4) a strategy called Training Knowledge Augmentation (TKA) that exploits the annotated first action cycle information from the entire dataset. This allows the network to harness shared characteristics across actions effectively, thereby enhancing model performance and generalizability to unseen actions. Experimental results demonstrate that our approach achieves superior outcomes on RepCount-A and related datasets, highlighting the efficacy of our framework in improving model performance on seen and unseen actions. Our paper makes significant contributions to the field of action counting by addressing the limitations of existing datasets and proposing novel techniques for improving model generalizability.

Yuting Xiao, Jiale Xu, Shenghua Gao

Benefiting from the continuous representation ability, deep implicit functions can represent a shape at infinite resolution. However, extracting high-resolution iso-surface from an implicit function requires forward-propagating a network with a large number of parameters for numerous query points, thus preventing the generation speed. Inspired by the Taylor series, we propose Taylo3DNet to accelerate the inference of implicit shape representations. Taylor3DNet exploits a set of discrete landmark points and their corresponding Taylor series coefficients to represent the implicit field of a 3D shape, and the number of landmark points is independent of the resolution of the iso-surface extraction. Once the coefficients corresponding to the landmark points are predicted, the network evaluation for each query point can be simplified as a low-order Taylor series calculation with several nearest landmark points. Based on this efficient representation, our Taylor3DNet achieves a significantly faster inference speed than classical network-based implicit functions. We evaluate our approach on reconstruction tasks with various input types, and the results demonstrate that our approach can improve the inference speed by a large margin without sacrificing the performance compared with state-of-the-art baselines.

Yicheng Qian, Weixin Luo, Dongze Lian et al.

In this paper, we propose a novel sequence verification task that aims to distinguish positive video pairs performing the same action sequence from negative ones with step-level transformations but still conducting the same task. Such a challenging task resides in an open-set setting without prior action detection or segmentation that requires event-level or even frame-level annotations. To that end, we carefully reorganize two publicly available action-related datasets with step-procedure-task structure. To fully investigate the effectiveness of any method, we collect a scripted video dataset enumerating all kinds of step-level transformations in chemical experiments. Besides, a novel evaluation metric Weighted Distance Ratio is introduced to ensure equivalence for different step-level transformations during evaluation. In the end, a simple but effective baseline based on the transformer encoder with a novel sequence alignment loss is introduced to better characterize long-term dependency between steps, which outperforms other action recognition methods. Codes and data will be released.

Pingxuan Huang, Zhenhua Cui, Jing Li et al.

Most pedestrian trajectory prediction methods rely on a huge amount of trajectories annotation, which is time-consuming and expensive. Moreover, a well-trained model may not effectively generalize to a new scenario captured by another camera. Therefore, it is desirable to adapt the model trained on an annotated source domain to the target domain. To achieve domain adaptation for trajectory prediction, we propose a Cross-domain Trajectory Prediction Network (CTP-Net). In this framework, encoders are used in both domains to encode the observed trajectories, then their features are aligned by a cross-domain feature discriminator. Further, considering the consistency between the observed and the predicted trajectories, a target domain offset discriminator is utilized to adversarially regularize the future trajectory predictions to be in line with the observed trajectories. Extensive experiments demonstrate the effectiveness of our method on domain adaptation for pedestrian trajectory prediction.

Kang Zhou, Jing Li, Weixin Luo et al.

Anomaly detection in medical images refers to the identification of abnormal images with only normal images in the training set. Most existing methods solve this problem with a self-reconstruction framework, which tends to learn an identity mapping and reduces the sensitivity to anomalies. To mitigate this problem, in this paper, we propose a novel Proxy-bridged Image Reconstruction Network (ProxyAno) for anomaly detection in medical images. Specifically, we use an intermediate proxy to bridge the input image and the reconstructed image. We study different proxy types, and we find that the superpixel-image (SI) is the best one. We set all pixels' intensities within each superpixel as their average intensity, and denote this image as SI. The proposed ProxyAno consists of two modules, a Proxy Extraction Module and an Image Reconstruction Module. In the Proxy Extraction Module, a memory is introduced to memorize the feature correspondence for normal image to its corresponding SI, while the memorized correspondence does not apply to the abnormal images, which leads to the information loss for abnormal image and facilitates the anomaly detection. In the Image Reconstruction Module, we map an SI to its reconstructed image. Further, we crop a patch from the image and paste it on the normal SI to mimic the anomalies, and enforce the network to reconstruct the normal image even with the pseudo abnormal SI. In this way, our network enlarges the reconstruction error for anomalies. Extensive experiments on brain MR images, retinal OCT images and retinal fundus images verify the effectiveness of our method for both image-level and pixel-level anomaly detection.

Xianing Chen, Chunlin Xu, Qiong Cao et al.

Transformers have shown preferable performance on many vision tasks. However, for the task of person re-identification (ReID), vanilla transformers leave the rich contexts on high-order feature relations under-exploited and deteriorate local feature details, which are insufficient due to the dramatic variations of pedestrians. In this work, we propose an Omni-Relational High-Order Transformer (OH-Former) to model omni-relational features for ReID. First, to strengthen the capacity of visual representation, instead of obtaining the attention matrix based on pairs of queries and isolated keys at each spatial location, we take a step further to model high-order statistics information for the non-local mechanism. We share the attention weights in the corresponding layer of each order with a prior mixing mechanism to reduce the computation cost. Then, a convolution-based local relation perception module is proposed to extract the local relations and 2D position information. The experimental results of our model are superior promising, which show state-of-the-art performance on Market-1501, DukeMTMC, MSMT17 and Occluded-Duke datasets.

Shenhan Qian, Zhi Tu, Yihao Zhi et al.

Co-speech gesture generation is to synthesize a gesture sequence that not only looks real but also matches with the input speech audio. Our method generates the movements of a complete upper body, including arms, hands, and the head. Although recent data-driven methods achieve great success, challenges still exist, such as limited variety, poor fidelity, and lack of objective metrics. Motivated by the fact that the speech cannot fully determine the gesture, we design a method that learns a set of gesture template vectors to model the latent conditions, which relieve the ambiguity. For our method, the template vector determines the general appearance of a generated gesture sequence, while the speech audio drives subtle movements of the body, both indispensable for synthesizing a realistic gesture sequence. Due to the intractability of an objective metric for gesture-speech synchronization, we adopt the lip-sync error as a proxy metric to tune and evaluate the synchronization ability of our model. Extensive experiments show the superiority of our method in both objective and subjective evaluations on fidelity and synchronization.

Binbin Huang, Dongze Lian, Weixin Luo et al.

An LBYL (`Look Before You Leap') Network is proposed for end-to-end trainable one-stage visual grounding. The idea behind LBYL-Net is intuitive and straightforward: we follow a language's description to localize the target object based on its relative spatial relation to `Landmarks', which is characterized by some spatial positional words and some descriptive words about the object. The core of our LBYL-Net is a landmark feature convolution module that transmits the visual features with the guidance of linguistic description along with different directions. Consequently, such a module encodes the relative spatial positional relations between the current object and its context. Then we combine the contextual information from the landmark feature convolution module with the target's visual features for grounding. To make this landmark feature convolution light-weight, we introduce a dynamic programming algorithm (termed dynamic max pooling) with low complexity to extract the landmark feature. Thanks to the landmark feature convolution module, we mimic the human behavior of `Look Before You Leap' to design an LBYL-Net, which takes full consideration of contextual information. Extensive experiments show our method's effectiveness in four grounding datasets. Specifically, our LBYL-Net outperforms all state-of-the-art two-stage and one-stage methods on ReferitGame. On RefCOCO and RefCOCO+, Our LBYL-Net also achieves comparable results or even better results than existing one-stage methods.