no code implementations • 16 Jun 2025 • Weimin Bai, Yubo Li, Wenzheng Chen, Weijian Luo, He Sun
Distilling pre-trained 2D diffusion models into 3D assets has driven remarkable advances in text-to-3D synthesis.
no code implementations • 11 Jun 2025 • Haoru Wang, Kai Ye, Yangyan Li, Wenzheng Chen, Baoquan Chen
Motivated by and following this trend, we propose a novel NVS framework that minimizes 3D inductive bias and pose dependence for both input and target views.
no code implementations • CVPR 2025 • Qiyu Dai, Xingyu Ni, Qianfan Shen, Wenzheng Chen, Baoquan Chen, Mengyu Chu
In this work, we introduce RainyGS, a novel approach that leverages the strengths of both physics-based modeling and 3DGS to generate photorealistic, dynamic rain effects in open-world scenes with physical accuracy.
1 code implementation • CVPR 2025 • Li Jin, Yujie Wang, Wenzheng Chen, Qiyu Dai, Qingzhe Gao, Xueying Qin, Baoquan Chen
We address this by introducing the first one-shot category-level object canonicalization framework that operates under arbitrary poses, requiring only a single canonical model as a reference (the "prior model") for each category.
no code implementations • 31 Oct 2024 • Kai Ye, Chong Gao, Guanbin Li, Wenzheng Chen, Baoquan Chen
While recent 3DGS methods have achieved remarkable results in novel view synthesis (NVS), accurately capturing high-fidelity geometry, physically interpretable materials and lighting remains challenging, as it requires precise geometry modeling to provide accurate surface normals, along with physically-based rendering (PBR) techniques to ensure correct material and lighting disentanglement.
no code implementations • 15 Oct 2024 • Weimin Bai, Weiheng Tang, Enze Ye, Siyi Chen, Wenzheng Chen, He Sun
Diffusion models have demonstrated exceptional ability in modeling complex image distributions, making them versatile plug-and-play priors for solving imaging inverse problems.
no code implementations • 15 Jul 2024 • Yifei Wang, Weimin Bai, Weijian Luo, Wenzheng Chen, He Sun
The conditional normalizing flow try to learn to recover clean images through a novel amortized inference mechanism, and can thus effectively facilitate the diffusion model's training with corrupted data.
no code implementations • 1 Jul 2024 • Weimin Bai, Siyi Chen, Wenzheng Chen, He Sun
Additionally, many current approaches rely on pixel-space diffusion models, leaving the potential of more powerful latent diffusion models (LDMs) underexplored.
no code implementations • 1 Jul 2024 • Weimin Bai, Yifei Wang, Wenzheng Chen, He Sun
Diffusion models excel in solving imaging inverse problems due to their ability to model complex image priors.
1 code implementation • 5 Feb 2024 • Yuanxing Duan, Fangyin Wei, Qiyu Dai, Yuhang He, Wenzheng Chen, Baoquan Chen
We consider the problem of novel-view synthesis (NVS) for dynamic scenes.
no code implementations • CVPR 2024 • Parsa Mirdehghan, Maxx Wu, Wenzheng Chen, David B. Lindell, Kiriakos N. Kutulakos
We show how to turn a noisy and fragile active triangulation technique--three-pattern structured light with a grayscale camera--into a fast and powerful tool for 3D capture: able to output sub-pixel accurate disparities at megapixel resolution along with reflectance normals and a no-reference estimate of its own pixelwise 3D error.
no code implementations • ICCV 2023 • Tzofi Klinghoffer, Jonah Philion, Wenzheng Chen, Or Litany, Zan Gojcic, Jungseock Joo, Ramesh Raskar, Sanja Fidler, Jose M. Alvarez
We introduce a technique for novel view synthesis and use it to transform collected data to the viewpoint of target rigs, allowing us to train BEV segmentation models for diverse target rigs without any additional data collection or labeling cost.
1 code implementation • 10 Aug 2023 • Tianchang Shen, Jacob Munkberg, Jon Hasselgren, Kangxue Yin, Zian Wang, Wenzheng Chen, Zan Gojcic, Sanja Fidler, Nicholas Sharp, Jun Gao
This work considers gradient-based mesh optimization, where we iteratively optimize for a 3D surface mesh by representing it as the isosurface of a scalar field, an increasingly common paradigm in applications including photogrammetry, generative modeling, and inverse physics.
no code implementations • 21 Apr 2023 • Binbin Huang, Xingyue Peng, Siyuan Shen, Suan Xia, Ruiqian Li, Yanhua Yu, Yuehan Wang, Shenghua Gao, Wenzheng Chen, Shiying Li, Jingyi Yu
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.
no code implementations • 6 Apr 2023 • Zian Wang, Tianchang Shen, Jun Gao, Shengyu Huang, Jacob Munkberg, Jon Hasselgren, Zan Gojcic, Wenzheng Chen, Sanja Fidler
Reconstruction and intrinsic decomposition of scenes from captured imagery would enable many applications such as relighting and virtual object insertion.
no code implementations • CVPR 2023 • Zian Wang, Tianchang Shen, Jun Gao, Shengyu Huang, Jacob Munkberg, Jon Hasselgren, Zan Gojcic, Wenzheng Chen, Sanja Fidler
Reconstruction and intrinsic decomposition of scenes from captured imagery would enable many applications such as relighting and virtual object insertion.
no code implementations • CVPR 2023 • Taotao Zhou, Kai He, Di wu, Teng Xu, Qixuan Zhang, Kuixiang Shao, Wenzheng Chen, Lan Xu, Jingyi Yu
UltraStage will be publicly available to the community to stimulate significant future developments in various human modeling and rendering tasks.
no code implementations • CVPR 2023 • Suyi Jiang, Haoran Jiang, Ziyu Wang, Haimin Luo, Wenzheng Chen, Lan Xu
With the aid of the anchor image, we adapt a 3D reconstructor for fine-grained details synthesis and propose a two-stage blending scheme to boost appearance generation.
3 code implementations • 22 Sep 2022 • Jun Gao, Tianchang Shen, Zian Wang, Wenzheng Chen, Kangxue Yin, Daiqing Li, Or Litany, Zan Gojcic, Sanja Fidler
As several industries are moving towards modeling massive 3D virtual worlds, the need for content creation tools that can scale in terms of the quantity, quality, and diversity of 3D content is becoming evident.
no code implementations • 19 Aug 2022 • Zian Wang, Wenzheng Chen, David Acuna, Jan Kautz, Sanja Fidler
In this work, we propose a neural approach that estimates the 5D HDR light field from a single image, and a differentiable object insertion formulation that enables end-to-end training with image-based losses that encourage realism.
no code implementations • 3 Jul 2022 • Youjia Wang, Teng Xu, Yiwen Wu, Minzhang Li, Wenzheng Chen, Lan Xu, Jingyi Yu
We extend Total Relighting to fix this problem by unifying its multi-view input normal maps with the physical face model.
2 code implementations • CVPR 2022 • Jacob Munkberg, Jon Hasselgren, Tianchang Shen, Jun Gao, Wenzheng Chen, Alex Evans, Thomas Müller, Sanja Fidler
We present an efficient method for joint optimization of topology, materials and lighting from multi-view image observations.
Ranked #2 on
Depth Prediction
on Stanford-ORB
no code implementations • NeurIPS 2021 • Wenzheng Chen, Joey Litalien, Jun Gao, Zian Wang, Clement Fuji Tsang, Sameh Khamis, Or Litany, Sanja Fidler
We consider the challenging problem of predicting intrinsic object properties from a single image by exploiting differentiable renderers.
1 code implementation • NeurIPS 2020 • Jun Gao, Wenzheng Chen, Tommy Xiang, Clement Fuji Tsang, Alec Jacobson, Morgan McGuire, Sanja Fidler
We introduce Deformable Tetrahedral Meshes (DefTet) as a particular parameterization that utilizes volumetric tetrahedral meshes for the reconstruction problem.
no code implementations • ICLR 2021 • Yuxuan Zhang, Wenzheng Chen, Huan Ling, Jun Gao, Yinan Zhang, Antonio Torralba, Sanja Fidler
Key to our approach is to exploit GANs as a multi-view data generator to train an inverse graphics network using an off-the-shelf differentiable renderer, and the trained inverse graphics network as a teacher to disentangle the GAN's latent code into interpretable 3D properties.
no code implementations • CVPR 2020 • Wenzheng Chen, Parsa Mirdehghan, Sanja Fidler, Kiriakos N. Kutulakos
We consider the problem of optimizing the performance of an active imaging system by automatically discovering the illuminations it should use, and the way to decode them.
6 code implementations • 12 Nov 2019 • Krishna Murthy Jatavallabhula, Edward Smith, Jean-Francois Lafleche, Clement Fuji Tsang, Artem Rozantsev, Wenzheng Chen, Tommy Xiang, Rev Lebaredian, Sanja Fidler
We present Kaolin, a PyTorch library aiming to accelerate 3D deep learning research.
1 code implementation • NeurIPS 2019 • Wenzheng Chen, Jun Gao, Huan Ling, Edward J. Smith, Jaakko Lehtinen, Alec Jacobson, Sanja Fidler
Many machine learning models operate on images, but ignore the fact that images are 2D projections formed by 3D geometry interacting with light, in a process called rendering.
Ranked #4 on
Single-View 3D Reconstruction
on ShapeNet
2 code implementations • CVPR 2019 • Huan Ling, Jun Gao, Amlan Kar, Wenzheng Chen, Sanja Fidler
Our model runs at 29. 3ms in automatic, and 2. 6ms in interactive mode, making it 10x and 100x faster than Polygon-RNN++.
no code implementations • CVPR 2019 • Wenzheng Chen, Simon Daneau, Fahim Mannan, Felix Heide
Relying on consumer color image sensors, with high fill factor, high quantum efficiency and low read-out noise, we demonstrate high-fidelity color NLOS imaging for scene configurations tackled before with picosecond time resolution.
no code implementations • CVPR 2018 • Parsa Mirdehghan, Wenzheng Chen, Kiriakos N. Kutulakos
We consider the problem of automatically generating sequences of structured-light patterns for active stereo triangulation of a static scene.
no code implementations • 18 Aug 2016 • Huayong Xu, Yangyan Li, Wenzheng Chen, Dani Lischinski, Daniel Cohen-Or, Baoquan Chen
We show that the resulting P-maps may be used to evaluate how likely a rectangle proposal is to contain an instance of the class, and further process good proposals to produce an accurate object cutout mask.
no code implementations • 10 Apr 2016 • Wenzheng Chen, Huan Wang, Yangyan Li, Hao Su, Zhenhua Wang, Changhe Tu, Dani Lischinski, Daniel Cohen-Or, Baoquan Chen
Human 3D pose estimation from a single image is a challenging task with numerous applications.