Yuchi Huo

Jingsen Zhu, Fujun Luan, Yuchi Huo et al.

Indoor scenes typically exhibit complex, spatially-varying appearance from global illumination, making inverse rendering a challenging ill-posed problem. This work presents an end-to-end, learning-based inverse rendering framework incorporating differentiable Monte Carlo raytracing with importance sampling. The framework takes a single image as input to jointly recover the underlying geometry, spatially-varying lighting, and photorealistic materials. Specifically, we introduce a physically-based differentiable rendering layer with screen-space ray tracing, resulting in more realistic specular reflections that match the input photo. In addition, we create a large-scale, photorealistic indoor scene dataset with significantly richer details like complex furniture and dedicated decorations. Further, we design a novel out-of-view lighting network with uncertainty-aware refinement leveraging hypernetwork-based neural radiance fields to predict lighting outside the view of the input photo. Through extensive evaluations on common benchmark datasets, we demonstrate superior inverse rendering quality of our method compared to state-of-the-art baselines, enabling various applications such as complex object insertion and material editing with high fidelity. Code and data will be made available at \url{https://jingsenzhu.github.io/invrend}.

Jingsen Zhu, Yuchi Huo, Qi Ye et al.

In this work, we present I$^2$-SDF, a new method for intrinsic indoor scene reconstruction and editing using differentiable Monte Carlo raytracing on neural signed distance fields (SDFs). Our holistic neural SDF-based framework jointly recovers the underlying shapes, incident radiance and materials from multi-view images. We introduce a novel bubble loss for fine-grained small objects and error-guided adaptive sampling scheme to largely improve the reconstruction quality on large-scale indoor scenes. Further, we propose to decompose the neural radiance field into spatially-varying material of the scene as a neural field through surface-based, differentiable Monte Carlo raytracing and emitter semantic segmentations, which enables physically based and photorealistic scene relighting and editing applications. Through a number of qualitative and quantitative experiments, we demonstrate the superior quality of our method on indoor scene reconstruction, novel view synthesis, and scene editing compared to state-of-the-art baselines.

Guoyuan An, Woo Jae Kim, Saelyne Yang et al.

This paper introduces the first two pixel retrieval benchmarks. Pixel retrieval is segmented instance retrieval. Like semantic segmentation extends classification to the pixel level, pixel retrieval is an extension of image retrieval and offers information about which pixels are related to the query object. In addition to retrieving images for the given query, it helps users quickly identify the query object in true positive images and exclude false positive images by denoting the correlated pixels. Our user study results show pixel-level annotation can significantly improve the user experience. Compared with semantic and instance segmentation, pixel retrieval requires a fine-grained recognition capability for variable-granularity targets. To this end, we propose pixel retrieval benchmarks named PROxford and PRParis, which are based on the widely used image retrieval datasets, ROxford and RParis. Three professional annotators label 5,942 images with two rounds of double-checking and refinement. Furthermore, we conduct extensive experiments and analysis on the SOTA methods in image search, image matching, detection, segmentation, and dense matching using our pixel retrieval benchmarks. Results show that the pixel retrieval task is challenging to these approaches and distinctive from existing problems, suggesting that further research can advance the content-based pixel-retrieval and thus user search experience. The datasets can be downloaded from \href{https://github.com/anguoyuan/Pixel_retrieval-Segmented_instance_retrieval}{this link}.

Xu Yin, Dongbo Min, Yuchi Huo et al.

With increasing demands for high-quality semantic segmentation in the industry, hard-distinguishing semantic boundaries have posed a significant threat to existing solutions. Inspired by real-life experience, i.e., combining varied observations contributes to higher visual recognition confidence, we present the equipotential learning (EPL) method. This novel module transfers the predicted/ground-truth semantic labels to a self-defined potential domain to learn and infer decision boundaries along customized directions. The conversion to the potential domain is implemented via a lightweight differentiable anisotropic convolution without incurring any parameter overhead. Besides, the designed two loss functions, the point loss and the equipotential line loss implement anisotropic field regression and category-level contour learning, respectively, enhancing prediction consistencies in the inter/intra-class boundary areas. More importantly, EPL is agnostic to network architectures, and thus it can be plugged into most existing segmentation models. This paper is the first attempt to address the boundary segmentation problem with field regression and contour learning. Meaningful performance improvements on Pascal Voc 2012 and Cityscapes demonstrate that the proposed EPL module can benefit the off-the-shelf fully convolutional network models when recognizing semantic boundary areas. Besides, intensive comparisons and analysis show the favorable merits of EPL for distinguishing semantically-similar and irregular-shaped categories.

Fuzhi Zhong, Rui Wang, Yuchi Huo et al.

Recent work on the intrinsic image of humans starts to consider the visibility of incident illumination and encodes the light transfer function by spherical harmonics. In this paper, we show that such a light transfer function can be further decomposed into visibility and cosine terms related to surface normal. Such decomposition allows us to recover the surface normal in addition to visibility. We propose a deep learning-based approach with a reconstruction loss for training on real-world images. Results show that compared with previous works, the reconstruction of human face from our method better reveals the surface normal and shading details especially around regions where visibility effect is strong.

Haoming Li, Xinzhuo Lin, Yang Zhou et al.

3D grasp synthesis generates grasping poses given an input object. Existing works tackle the problem by learning a direct mapping from objects to the distributions of grasping poses. However, because the physical contact is sensitive to small changes in pose, the high-nonlinear mapping between 3D object representation to valid poses is considerably non-smooth, leading to poor generation efficiency and restricted generality. To tackle the challenge, we introduce an intermediate variable for grasp contact areas to constrain the grasp generation; in other words, we factorize the mapping into two sequential stages by assuming that grasping poses are fully constrained given contact maps: 1) we first learn contact map distributions to generate the potential contact maps for grasps; 2) then learn a mapping from the contact maps to the grasping poses. Further, we propose a penetration-aware optimization with the generated contacts as a consistency constraint for grasp refinement. Extensive validations on two public datasets show that our method outperforms state-of-the-art methods regarding grasp generation on various metrics.

Anjun Chen, Xiangyu Wang, Kun Shi et al.

3D human reconstruction from RGB images achieves decent results in good weather conditions but degrades dramatically in rough weather. Complementary, mmWave radars have been employed to reconstruct 3D human joints and meshes in rough weather. However, combining RGB and mmWave signals for robust all-weather 3D human reconstruction is still an open challenge, given the sparse nature of mmWave and the vulnerability of RGB images. In this paper, we present ImmFusion, the first mmWave-RGB fusion solution to reconstruct 3D human bodies in all weather conditions robustly. Specifically, our ImmFusion consists of image and point backbones for token feature extraction and a Transformer module for token fusion. The image and point backbones refine global and local features from original data, and the Fusion Transformer Module aims for effective information fusion of two modalities by dynamically selecting informative tokens. Extensive experiments on a large-scale dataset, mmBody, captured in various environments demonstrate that ImmFusion can efficiently utilize the information of two modalities to achieve a robust 3D human body reconstruction in all weather conditions. In addition, our method's accuracy is significantly superior to that of state-of-the-art Transformer-based LiDAR-camera fusion methods.

Zhihua Zhong, Jingsen Zhu, Yuxin Dai et al.

The workload of real-time rendering is steeply increasing as the demand for high resolution, high refresh rates, and high realism rises, overwhelming most graphics cards. To mitigate this problem, one of the most popular solutions is to render images at a low resolution to reduce rendering overhead, and then manage to accurately upsample the low-resolution rendered image to the target resolution, a.k.a. super-resolution techniques. Most existing methods focus on exploiting information from low-resolution inputs, such as historical frames. The absence of high frequency details in those LR inputs makes them hard to recover fine details in their high-resolution predictions. In this paper, we propose an efficient and effective super-resolution method that predicts high-quality upsampled reconstructions utilizing low-cost high-resolution auxiliary G-Buffers as additional input. With LR images and HR G-buffers as input, the network requires to align and fuse features at multi resolution levels. We introduce an efficient and effective H-Net architecture to solve this problem and significantly reduce rendering overhead without noticeable quality deterioration. Experiments show that our method is able to produce temporally consistent reconstructions in $4 \times 4$ and even challenging $8 \times 8$ upsampling cases at 4K resolution with real-time performance, with substantially improved quality and significant performance boost compared to existing works.

Xiangyu Wang, Jingsen Zhu, Qi Ye et al.

With the popularity of implicit neural representations, or neural radiance fields (NeRF), there is a pressing need for editing methods to interact with the implicit 3D models for tasks like post-processing reconstructed scenes and 3D content creation. While previous works have explored NeRF editing from various perspectives, they are restricted in editing flexibility, quality, and speed, failing to offer direct editing response and instant preview. The key challenge is to conceive a locally editable neural representation that can directly reflect the editing instructions and update instantly. To bridge the gap, we propose a new interactive editing method and system for implicit representations, called Seal-3D, which allows users to edit NeRF models in a pixel-level and free manner with a wide range of NeRF-like backbone and preview the editing effects instantly. To achieve the effects, the challenges are addressed by our proposed proxy function mapping the editing instructions to the original space of NeRF models in the teacher model and a two-stage training strategy for the student model with local pretraining and global finetuning. A NeRF editing system is built to showcase various editing types. Our system can achieve compelling editing effects with an interactive speed of about 1 second.

Guoyuan An, Juhyung Seon, Inkyu An et al.

This paper presents an innovative approach to enhancing explainable image retrieval, particularly in situations where a fine-tuning set is unavailable. The widely-used SPatial verification (SP) method, despite its efficacy, relies on a spatial model and the hypothesis-testing strategy for instance recognition, leading to inherent limitations, including the assumption of planar structures and neglect of topological relations among features. To address these shortcomings, we introduce a pioneering technique that replaces the spatial model with a topological one within the RANSAC process. We propose bio-inspired saccade and fovea functions to verify the topological consistency among features, effectively circumventing the issues associated with SP's spatial model. Our experimental results demonstrate that our method significantly outperforms SP, achieving state-of-the-art performance in non-fine-tuning retrieval. Furthermore, our approach can enhance performance when used in conjunction with fine-tuned features. Importantly, our method retains high explainability and is lightweight, offering a practical and adaptable solution for a variety of real-world applications.

Xu Yin, Fei Pan, Guoyuan An et al.

Existing open-set recognition (OSR) studies typically assume that each image contains only one class label, with the unknown test set (negative) having a disjoint label space from the known test set (positive), a scenario referred to as full-label shift. This paper introduces the mixed OSR problem, where test images contain multiple class semantics, with both known and unknown classes co-occurring in the negatives, leading to a more complex super-label shift that better reflects real-world scenarios. To tackle this challenge, we propose the OpenSlot framework, based on object-centric learning, which uses slot features to represent diverse class semantics and generate class predictions. The proposed anti-noise slot (ANS) technique helps mitigate the impact of noise (invalid or background) slots during classification training, addressing the semantic misalignment between class predictions and ground truth. We evaluate OpenSlot on both mixed and conventional OSR benchmarks. Without elaborate designs, our method not only excels existing approaches in detecting super-label shifts across OSR tasks, but also achieves state-of-the-art performance on conventional benchmarks. Meanwhile, OpenSlot can localize class objects without using bounding boxes during training, demonstrating competitive performance in open-set object detection and potential for generalization.

Zixuan Xie, Rengan Xie, Rong Li et al.

In this work, we use multi-view aerial images to reconstruct the geometry, lighting, and material of facades using neural signed distance fields (SDFs). Without the requirement of complex equipment, our method only takes simple RGB images captured by a drone as inputs to enable physically based and photorealistic novel-view rendering, relighting, and editing. However, a real-world facade usually has complex appearances ranging from diffuse rocks with subtle details to large-area glass windows with specular reflections, making it hard to attend to everything. As a result, previous methods can preserve the geometry details but fail to reconstruct smooth glass windows or verse vise. In order to address this challenge, we introduce three spatial- and semantic-adaptive optimization strategies, including a semantic regularization approach based on zero-shot segmentation techniques to improve material consistency, a frequency-aware geometry regularization to balance surface smoothness and details in different surfaces, and a visibility probe-based scheme to enable efficient modeling of the local lighting in large-scale outdoor environments. In addition, we capture a real-world facade aerial 3D scanning image set and corresponding point clouds for training and benchmarking. The experiment demonstrates the superior quality of our method on facade holistic inverse rendering, novel view synthesis, and scene editing compared to state-of-the-art baselines.

Zhi He, Rui Wang, Wei Hua et al.

This paper propose a interactive 3D modeling method and corresponding system based on single or multiple uncalibrated images. The main feature of this method is that, according to the modeling habits of ordinary people, the 3D model of the target is reconstructed from coarse to fine images. On the basis of determining the approximate shape, the user adds or modify projection constraints and spatial constraints, and apply topology modification, gradually realize camera calibration, refine rough model, and finally complete the reconstruction of objects with arbitrary geometry and topology. During the interactive process, the geometric parameters and camera projection matrix are solved in real time, and the reconstruction results are displayed in a 3D window.

Zhizhen Wu, Zhe Cao, Yuchi Huo

Image convolution with complex kernels is a fundamental operation in photography, scientific imaging, and animation effects, yet direct dense convolution is computationally prohibitive on resource-limited devices. Existing approximations, such as simulated annealing or low-rank decompositions, either lack efficiency or fail to capture non-convex kernels. We introduce a differentiable kernel decomposition framework that represents a target spatially-variant, dense, complex kernel using a set of sparse kernel samples. Our approach features (i) a decomposition that enables differentiable optimization of sparse kernels, (ii) a dedicated initialization strategy for non-convex shapes to avoid poor local minima, and (iii) a kernel-space interpolation scheme that extends single-kernel filtering to spatially varying filtering without retraining and additional runtime overhead. Experiments on Gaussian and non-convex kernels show that our method achieves higher fidelity than simulated annealing and significantly lower cost than low-rank decompositions. Our approach provides a practical solution for mobile imaging and real-time rendering, while remaining fully differentiable for integration into broader learning pipelines.

Dianbing Xi, Jiepeng Wang, Yuanzhi Liang et al.

We tackle the dual challenges of video understanding and controllable video generation within a unified diffusion framework. Our key insights are two-fold: geometry-only cues (e.g., depth, edges) are insufficient: they specify layout but under-constrain appearance, materials, and illumination, limiting physically meaningful edits such as relighting or material swaps and often causing temporal drift. Enriching the model with additional graphics-based modalities (intrinsics and semantics) provides complementary constraints that both disambiguate understanding and enable precise, predictable control during generation. However, building a single model that uses many heterogeneous cues introduces two core difficulties. Architecturally, the model must accept any subset of modalities, remain robust to missing inputs, and inject control signals without sacrificing temporal consistency. Data-wise, training demands large-scale, temporally aligned supervision that ties real videos to per-pixel multimodal annotations. We then propose CtrlVDiff, a unified diffusion model trained with a Hybrid Modality Control Strategy (HMCS) that routes and fuses features from depth, normals, segmentation, edges, and graphics-based intrinsics (albedo, roughness, metallic), and re-renders videos from any chosen subset with strong temporal coherence. To enable this, we build MMVideo, a hybrid real-and-synthetic dataset aligned across modalities and captions. Across understanding and generation benchmarks, CtrlVDiff delivers superior controllability and fidelity, enabling layer-wise edits (relighting, material adjustment, object insertion) and surpassing state-of-the-art baselines while remaining robust when some modalities are unavailable.

Anjun Chen, Xiangyu Wang, Zhi Xu et al.

Recent advancements in sensor technology and deep learning have led to significant progress in 3D human body reconstruction. However, most existing approaches rely on data from a specific sensor, which can be unreliable due to the inherent limitations of individual sensing modalities. Additionally, existing multi-modal fusion methods generally require customized designs based on the specific sensor combinations or setups, which limits the flexibility and generality of these methods. Furthermore, conventional point-image projection-based and Transformer-based fusion networks are susceptible to the influence of noisy modalities and sensor poses. To address these limitations and achieve robust 3D human body reconstruction in various conditions, we propose AdaptiveFusion, a generic adaptive multi-modal multi-view fusion framework that can effectively incorporate arbitrary combinations of uncalibrated sensor inputs. By treating different modalities from various viewpoints as equal tokens, and our handcrafted modality sampling module by leveraging the inherent flexibility of Transformer models, AdaptiveFusion is able to cope with arbitrary numbers of inputs and accommodate noisy modalities with only a single training network. Extensive experiments on large-scale human datasets demonstrate the effectiveness of AdaptiveFusion in achieving high-quality 3D human body reconstruction in various environments. In addition, our method achieves superior accuracy compared to state-of-the-art fusion methods.

Ruiyuan Zhang, Qi Wang, Jiaxiang Liu et al.

3D part assembly aims to understand part relationships and predict their 6-DoF poses to construct realistic 3D shapes, addressing the growing demand for autonomous assembly, which is crucial for robots. Existing methods mainly estimate the transformation of each part by training neural networks under supervision, which requires a substantial quantity of manually labeled data. However, the high cost of data collection and the immense variability of real-world shapes and parts make traditional methods impractical for large-scale applications. In this paper, we propose first a zero-shot part assembly method that utilizes pre-trained point cloud diffusion models as discriminators in the assembly process, guiding the manipulation of parts to form realistic shapes. Specifically, we theoretically demonstrate that utilizing a diffusion model for zero-shot part assembly can be transformed into an Iterative Closest Point (ICP) process. Then, we propose a novel pushing-away strategy to address the overlap parts, thereby further enhancing the robustness of the method. To verify our work, we conduct extensive experiments and quantitative comparisons to several strong baseline methods, demonstrating the effectiveness of the proposed approach, which even surpasses the supervised learning method. The code has been released on https://github.com/Ruiyuan-Zhang/Zero-Shot-Assembly.

Yuxin Dai, Qi Wang, Jingsen Zhu et al.

We present MIRReS, a novel two-stage inverse rendering framework that jointly reconstructs and optimizes the explicit geometry, material, and lighting from multi-view images. Unlike previous methods that rely on implicit irradiance fields or simplified path tracing algorithms, our method extracts an explicit geometry (triangular mesh) in stage one, and introduces a more realistic physically-based inverse rendering model that utilizes multi-bounce path tracing and Monte Carlo integration. By leveraging multi-bounce path tracing, our method effectively estimates indirect illumination, including self-shadowing and internal reflections, which improves the intrinsic decomposition of shape, material, and lighting. Moreover, we incorporate reservoir sampling into our framework to address the noise in Monte Carlo integration, enhancing convergence and facilitating gradient-based optimization with low sample counts. Through qualitative and quantitative evaluation of several scenarios, especially in challenging scenarios with complex shadows, we demonstrate that our method achieves state-of-the-art performance on decomposition results. Additionally, our optimized explicit geometry enables applications such as scene editing, relighting, and material editing with modern graphics engines or CAD software. The source code is available at https://brabbitdousha.github.io/MIRReS/

Qifeng Chen, Jiarun Liu, Rengan Xie et al.

Recent GS-based rendering has made significant progress for LiDAR, surpassing Neural Radiance Fields (NeRF) in both quality and speed. However, these methods exhibit artifacts in extrapolated novel view synthesis due to the incomplete reconstruction from single traversal scans. To address this limitation, we present LiDAR-GS++, a LiDAR Gaussian Splatting reconstruction method enhanced by diffusion priors for real-time and high-fidelity re-simulation on public urban roads. Specifically, we introduce a controllable LiDAR generation model conditioned on coarsely extrapolated rendering to produce extra geometry-consistent scans and employ an effective distillation mechanism for expansive reconstruction. By extending reconstruction to under-fitted regions, our approach ensures global geometric consistency for extrapolative novel views while preserving detailed scene surfaces captured by sensors. Experiments on multiple public datasets demonstrate that LiDAR-GS++ achieves state-of-the-art performance for both interpolated and extrapolated viewpoints, surpassing existing GS and NeRF-based methods.

Xinkai Yan, Jieting Xu, Yuchi Huo et al.

Neural rendering is a new image and video generation method based on deep learning. It combines the deep learning model with the physical knowledge of computer graphics, to obtain a controllable and realistic scene model, and realize the control of scene attributes such as lighting, camera parameters, posture and so on. On the one hand, neural rendering can not only make full use of the advantages of deep learning to accelerate the traditional forward rendering process, but also provide new solutions for specific tasks such as inverse rendering and 3D reconstruction. On the other hand, the design of innovative hardware structures that adapt to the neural rendering pipeline breaks through the parallel computing and power consumption bottleneck of existing graphics processors, which is expected to provide important support for future key areas such as virtual and augmented reality, film and television creation and digital entertainment, artificial intelligence and the metaverse. In this paper, we review the technical connotation, main challenges, and research progress of neural rendering. On this basis, we analyze the common requirements of neural rendering pipeline for hardware acceleration and the characteristics of the current hardware acceleration architecture, and then discuss the design challenges of neural rendering processor architecture. Finally, the future development trend of neural rendering processor architecture is prospected.

Yunlong Ran, Yanxu Li, Qi Ye et al.

Neural radiance field (NeRF) has achieved impressive results in high-quality 3D scene reconstruction. However, NeRF heavily relies on precise camera poses. While recent works like BARF have introduced camera pose optimization within NeRF, their applicability is limited to simple trajectory scenes. Existing methods struggle while tackling complex trajectories involving large rotations. To address this limitation, we propose CT-NeRF, an incremental reconstruction optimization pipeline using only RGB images without pose and depth input. In this pipeline, we first propose a local-global bundle adjustment under a pose graph connecting neighboring frames to enforce the consistency between poses to escape the local minima caused by only pose consistency with the scene structure. Further, we instantiate the consistency between poses as a reprojected geometric image distance constraint resulting from pixel-level correspondences between input image pairs. Through the incremental reconstruction, CT-NeRF enables the recovery of both camera poses and scene structure and is capable of handling scenes with complex trajectories. We evaluate the performance of CT-NeRF on two real-world datasets, NeRFBuster and Free-Dataset, which feature complex trajectories. Results show CT-NeRF outperforms existing methods in novel view synthesis and pose estimation accuracy.

Shijian Jiang, Qi Ye, Rengan Xie et al.

Our work aims to reconstruct a 3D object that is held and rotated by a hand in front of a static RGB camera. Previous methods that use implicit neural representations to recover the geometry of a generic hand-held object from multi-view images achieved compelling results in the visible part of the object. However, these methods falter in accurately capturing the shape within the hand-object contact region due to occlusion. In this paper, we propose a novel method that deals with surface reconstruction under occlusion by incorporating priors of 2D occlusion elucidation and physical contact constraints. For the former, we introduce an object amodal completion network to infer the 2D complete mask of objects under occlusion. To ensure the accuracy and view consistency of the predicted 2D amodal masks, we devise a joint optimization method for both amodal mask refinement and 3D reconstruction. For the latter, we impose penetration and attraction constraints on the local geometry in contact regions. We evaluate our approach on HO3D and HOD datasets and demonstrate that it outperforms the state-of-the-art methods in terms of reconstruction surface quality, with an improvement of $52\%$ on HO3D and $20\%$ on HOD. Project webpage: https://east-j.github.io/ihor.

Dianbing Xi, Jiepeng Wang, Yuanzhi Liang et al.

In this paper, we propose a novel framework for controllable video diffusion, OmniVDiff , aiming to synthesize and comprehend multiple video visual content in a single diffusion model. To achieve this, OmniVDiff treats all video visual modalities in the color space to learn a joint distribution, while employing an adaptive control strategy that dynamically adjusts the role of each visual modality during the diffusion process, either as a generation modality or a conditioning modality. Our framework supports three key capabilities: (1) Text-conditioned video generation, where all modalities are jointly synthesized from a textual prompt; (2) Video understanding, where structural modalities are predicted from rgb inputs in a coherent manner; and (3) X-conditioned video generation, where video synthesis is guided by finegrained inputs such as depth, canny and segmentation. Extensive experiments demonstrate that OmniVDiff achieves state-of-the-art performance in video generation tasks and competitive results in video understanding. Its flexibility and scalability make it well-suited for downstream applications such as video-to-video translation, modality adaptation for visual tasks, and scene reconstruction.

Yizheng Chen, Rengan Xie, Qi Ye et al.

Reconstructing 3D objects from a single image is an intriguing but challenging problem. One promising solution is to utilize multi-view (MV) 3D reconstruction to fuse generated MV images into consistent 3D objects. However, the generated images usually suffer from inconsistent lighting, misaligned geometry, and sparse views, leading to poor reconstruction quality. To cope with these problems, we present a novel 3D reconstruction framework that leverages intrinsic decomposition guidance, transient-mono prior guidance, and view augmentation to cope with the three issues, respectively. Specifically, we first leverage to decouple the shading information from the generated images to reduce the impact of inconsistent lighting; then, we introduce mono prior with view-dependent transient encoding to enhance the reconstructed normal; and finally, we design a view augmentation fusion strategy that minimizes pixel-level loss in generated sparse views and semantic loss in augmented random views, resulting in view-consistent geometry and detailed textures. Our approach, therefore, enables the integration of a pre-trained MV image generator and a neural network-based volumetric signed distance function (SDF) representation for a single image to 3D object reconstruction. We evaluate our framework on various datasets and demonstrate its superior performance in both quantitative and qualitative assessments, signifying a significant advancement in 3D object reconstruction. Compared with the latest state-of-the-art method Syncdreamer~\cite{liu2023syncdreamer}, we reduce the Chamfer Distance error by about 36\% and improve PSNR by about 30\% .

Dianbing Xi, Guoyuan An, Jingsen Zhu et al.

We propose PFAvatar (Pose-Fusion Avatar), a new method that reconstructs high-quality 3D avatars from Outfit of the Day(OOTD) photos, which exhibit diverse poses, occlusions, and complex backgrounds. Our method consists of two stages: (1) fine-tuning a pose-aware diffusion model from few-shot OOTD examples and (2) distilling a 3D avatar represented by a neural radiance field (NeRF). In the first stage, unlike previous methods that segment images into assets (e.g., garments, accessories) for 3D assembly, which is prone to inconsistency, we avoid decomposition and directly model the full-body appearance. By integrating a pre-trained ControlNet for pose estimation and a novel Condition Prior Preservation Loss (CPPL), our method enables end-to-end learning of fine details while mitigating language drift in few-shot training. Our method completes personalization in just 5 minutes, achieving a 48x speed-up compared to previous approaches. In the second stage, we introduce a NeRF-based avatar representation optimized by canonical SMPL-X space sampling and Multi-Resolution 3D-SDS. Compared to mesh-based representations that suffer from resolution-dependent discretization and erroneous occluded geometry, our continuous radiance field can preserve high-frequency textures (e.g., hair) and handle occlusions correctly through transmittance. Experiments demonstrate that PFAvatar outperforms state-of-the-art methods in terms of reconstruction fidelity, detail preservation, and robustness to occlusions/truncations, advancing practical 3D avatar generation from real-world OOTD albums. In addition, the reconstructed 3D avatar supports downstream applications such as virtual try-on, animation, and human video reenactment, further demonstrating the versatility and practical value of our approach.

Xu Yin, Min-Sung Yoon, Yuchi Huo et al.

Task execution for object rearrangement could be challenged by Task-Level Perturbations (TLP), i.e., unexpected object additions, removals, and displacements that can disrupt underlying visual policies and fundamentally compromise task feasibility and progress. To address these challenges, we present LangPert, a language-based framework designed to detect and mitigate TLP situations in tabletop rearrangement tasks. LangPert integrates a Visual Language Model (VLM) to comprehensively monitor policy's skill execution and environmental TLP, while leveraging the Hierarchical Chain-of-Thought (HCoT) reasoning mechanism to enhance the Large Language Model (LLM)'s contextual understanding and generate adaptive, corrective skill-execution plans. Our experimental results demonstrate that LangPert handles diverse TLP situations more effectively than baseline methods, achieving higher task completion rates, improved execution efficiency, and potential generalization to unseen scenarios.

Xu Yin, Woobin Im, Dongbo Min et al.

Generating reliable pseudo masks from image-level labels is challenging in the weakly supervised semantic segmentation (WSSS) task due to the lack of spatial information. Prevalent class activation map (CAM)-based solutions are challenged to discriminate the foreground (FG) objects from the suspicious background (BG) pixels (a.k.a. co-occurring) and learn the integral object regions. This paper proposes a simple fine-grained background representation (FBR) method to discover and represent diverse BG semantics and address the co-occurring problems. We abandon using the class prototype or pixel-level features for BG representation. Instead, we develop a novel primitive, negative region of interest (NROI), to capture the fine-grained BG semantic information and conduct the pixel-to-NROI contrast to distinguish the confusing BG pixels. We also present an active sampling strategy to mine the FG negatives on-the-fly, enabling efficient pixel-to-pixel intra-foreground contrastive learning to activate the entire object region. Thanks to the simplicity of design and convenience in use, our proposed method can be seamlessly plugged into various models, yielding new state-of-the-art results under various WSSS settings across benchmarks. Leveraging solely image-level (I) labels as supervision, our method achieves 73.2 mIoU and 45.6 mIoU segmentation results on Pascal Voc and MS COCO test sets, respectively. Furthermore, by incorporating saliency maps as an additional supervision signal (I+S), we attain 74.9 mIoU on Pascal Voc test set. Concurrently, our FBR approach demonstrates meaningful performance gains in weakly-supervised instance segmentation (WSIS) tasks, showcasing its robustness and strong generalization capabilities across diverse domains.

Guoyuan An, Yuchi Huo, Sung-Eui Yoon

This paper presents a novel method designed to enhance the efficiency and accuracy of both image retrieval and pixel retrieval. Traditional diffusion methods struggle to propagate spatial information effectively in conventional graphs due to their reliance on scalar edge weights. To overcome this limitation, we introduce a hypergraph-based framework, uniquely capable of efficiently propagating spatial information using local features during query time, thereby accurately retrieving and localizing objects within a database. Additionally, we innovatively utilize the structural information of the image graph through a technique we term "community selection". This approach allows for the assessment of the initial search result's uncertainty and facilitates an optimal balance between accuracy and speed. This is particularly crucial in real-world applications where such trade-offs are often necessary. Our experimental results, conducted on the (P)ROxford and (P)RParis datasets, demonstrate the significant superiority of our method over existing diffusion techniques. We achieve state-of-the-art (SOTA) accuracy in both image-level and pixel-level retrieval, while also maintaining impressive processing speed. This dual achievement underscores the effectiveness of our hypergraph-based framework and community selection technique, marking a notable advancement in the field of content-based image retrieval.

Qifeng Chen, Rengan Xie, Kai Huang et al.

Recently, implicit neural representation has been widely used to generate animatable human avatars. However, the materials and geometry of those representations are coupled in the neural network and hard to edit, which hinders their application in traditional graphics engines. We present a framework for acquiring human avatars that are attached with high-resolution physically-based material textures and triangular mesh from monocular video. Our method introduces a novel information fusion strategy to combine the information from the monocular video and synthesize virtual multi-view images to tackle the sparsity of the input view. We reconstruct humans as deformable neural implicit surfaces and extract triangle mesh in a well-behaved pose as the initial mesh of the next stage. In addition, we introduce an approach to correct the bias for the boundary and size of the coarse mesh extracted. Finally, we adapt prior knowledge of the latent diffusion model at super-resolution in multi-view to distill the decomposed texture. Experiments show that our approach outperforms previous representations in terms of high fidelity, and this explicit result supports deployment on common renderers.

Yuchi Huo

This manuscript discusses the extension of adaptive light field sampling with implicit radiance fields.

Haocheng Ren, Hao Zhang, Jia Zheng et al.

With the rapid development of data-driven techniques, data has played an essential role in various computer vision tasks. Many realistic and synthetic datasets have been proposed to address different problems. However, there are lots of unresolved challenges: (1) the creation of dataset is usually a tedious process with manual annotations, (2) most datasets are only designed for a single specific task, (3) the modification or randomization of the 3D scene is difficult, and (4) the release of commercial 3D data may encounter copyright issue. This paper presents MINERVAS, a Massive INterior EnviRonments VirtuAl Synthesis system, to facilitate the 3D scene modification and the 2D image synthesis for various vision tasks. In particular, we design a programmable pipeline with Domain-Specific Language, allowing users to (1) select scenes from the commercial indoor scene database, (2) synthesize scenes for different tasks with customized rules, and (3) render various imagery data, such as visual color, geometric structures, semantic label. Our system eases the difficulty of customizing massive numbers of scenes for different tasks and relieves users from manipulating fine-grained scene configurations by providing user-controllable randomness using multi-level samplers. Most importantly, it empowers users to access commercial scene databases with millions of indoor scenes and protects the copyright of core data assets, e.g., 3D CAD models. We demonstrate the validity and flexibility of our system by using our synthesized data to improve the performance on different kinds of computer vision tasks.

Soomin Kim, Yuchi Huo, Sung-Eui Yoon

Recently, deep learning-based single image reflection separation methods have been exploited widely. To benefit the learning approach, a large number of training image pairs (i.e., with and without reflections) were synthesized in various ways, yet they are away from a physically-based direction. In this paper, physically based rendering is used for faithfully synthesizing the required training images, and a corresponding network structure and loss term are proposed. We utilize existing RGBD/RGB images to estimate meshes, then physically simulate the light transportation between meshes, glass, and lens with path tracing to synthesize training data, which successfully reproduce the spatially variant anisotropic visual effect of glass reflection. For guiding the separation better, we additionally consider a module, backtrack network (BT-net) for backtracking the reflections, which removes complicated ghosting, attenuation, blurred and defocused effect of glass/lens. This enables obtaining a priori information before having the distortion. The proposed method considering additional a priori information with physically simulated training data is validated with various real reflection images and shows visually pleasant and numerical advantages compared with state-of-the-art techniques.

Yuchi Huo, Sung-Eui Yoon

We introduce an optical neural network system made by off-the-shelf components. In order to test the evaluate the physical property of the proposed system, we are making a prototype. After further discussions with our cooperators, we are agreed that the prototype implementation may take longer time than we expected earlier. Therefore we reach a consensus on withdrawing the paper until the physical data is available.