English
Related papers

Related papers: Differentiable Blocks World: Qualitative 3D Decomp…

200 papers

Many learning-based approaches have difficulty scaling to unseen data, as the generality of its learned prior is limited to the scale and variations of the training samples. This holds particularly true with 3D learning tasks, given the…

Computer Vision and Pattern Recognition · Computer Science 2020-12-15 Mingyue Yang , Yuxin Wen , Weikai Chen , Yongwei Chen , Kui Jia

Transient objects in video sequences can significantly degrade the quality of 3D scene reconstructions. To address this challenge, we propose T-3DGS, a novel framework that robustly filters out transient distractors during 3D reconstruction…

Computer Vision and Pattern Recognition · Computer Science 2025-03-11 Alexander Markin , Vadim Pryadilshchikov , Artem Komarichev , Ruslan Rakhimov , Peter Wonka , Evgeny Burnaev

Reconstruction of the soft tissues in robotic surgery from endoscopic stereo videos is important for many applications such as intra-operative navigation and image-guided robotic surgery automation. Previous works on this task mainly rely…

Computer Vision and Pattern Recognition · Computer Science 2022-07-01 Yuehao Wang , Yonghao Long , Siu Hin Fan , Qi Dou

We present a differentiable volume rendering solution that provides differentiability of all continuous parameters of the volume rendering process. This differentiable renderer is used to steer the parameters towards a setting with an…

Graphics · Computer Science 2022-07-26 Sebastian Weiss , Rüdiger Westermann

Reconstructing general dynamic scenes is important for many computer vision and graphics applications. Recent works represent the dynamic scene with neural radiance fields for photorealistic view synthesis, while their surface geometry is…

Computer Vision and Pattern Recognition · Computer Science 2023-03-02 Decai Chen , Haofei Lu , Ingo Feldmann , Oliver Schreer , Peter Eisert

Large-scale video generative models can synthesize diverse and realistic visual content for dynamic world creation, but they often lack element-wise controllability, hindering their use in editing scenes and training embodied AI agents. We…

Computer Vision and Pattern Recognition · Computer Science 2025-06-10 Sicheng Mo , Ziyang Leng , Leon Liu , Weizhen Wang , Honglin He , Bolei Zhou

As we begin to consider modeling large, realistic 3D building scenes, it becomes necessary to consider a more compact representation over the polygonal mesh model. Due to the large amounts of annotated training data, which is costly to…

Computer Vision and Pattern Recognition · Computer Science 2019-01-18 Xia Li , Yen-Liang Lin , James Miller , Alex Cheon , Walt Dixon

Visually exploring in a real-world 4D spatiotemporal space freely in VR has been a long-term quest. The task is especially appealing when only a few or even single RGB cameras are used for capturing the dynamic scene. To this end, we…

Computer Vision and Pattern Recognition · Computer Science 2023-02-21 Liangchen Song , Anpei Chen , Zhong Li , Zhang Chen , Lele Chen , Junsong Yuan , Yi Xu , Andreas Geiger

We propose a Transformer-based framework for 3D human texture estimation from a single image. The proposed Transformer is able to effectively exploit the global information of the input image, overcoming the limitations of existing methods…

Computer Vision and Pattern Recognition · Computer Science 2021-09-07 Xiangyu Xu , Chen Change Loy

We have recently seen tremendous progress in the neural advances for photo-real human modeling and rendering. However, it's still challenging to integrate them into an existing mesh-based pipeline for downstream applications. In this paper,…

In this paper, we present a novel, scalable approach for constructing open set, instance-level 3D scene representations, advancing open world understanding of 3D environments. Existing methods require pre-constructed 3D scenes and face…

Computer Vision and Pattern Recognition · Computer Science 2024-09-17 Rafay Mohiuddin , Sai Manoj Prakhya , Fiona Collins , Ziyuan Liu , André Borrmann

Recent point-based differentiable rendering techniques have achieved significant success in high-fidelity reconstruction and fast rendering. However, due to the unstructured nature of point-based representations, they are difficult to apply…

Graphics · Computer Science 2025-08-12 Kaiwen Song , Jinkai Cui , Zherui Qiu , Juyong Zhang

This paper proposes a new end-to-end neural rendering architecture to transfer appearance and reenact human actors. Our method leverages a carefully designed graph convolutional network (GCN) to model the human body manifold structure,…

Computer Vision and Pattern Recognition · Computer Science 2021-10-25 Thiago L. Gomes , Thiago M. Coutinho , Rafael Azevedo , Renato Martins , Erickson R. Nascimento

In recent years, substantial progress has been achieved in learning-based reconstruction of 3D objects. At the same time, generative models were proposed that can generate highly realistic images. However, despite this success in these…

Computer Vision and Pattern Recognition · Computer Science 2019-05-20 Michael Oechsle , Lars Mescheder , Michael Niemeyer , Thilo Strauss , Andreas Geiger

This paper addresses the limitations of neural rendering-based multi-view surface reconstruction methods, which require an additional mesh extraction step that is inconvenient and would produce poor-quality surfaces with mesh aliasing,…

Computer Vision and Pattern Recognition · Computer Science 2025-08-26 Qitong Zhang , Jieqing Feng

Radiance fields have emerged as a predominant representation for modeling 3D scene appearance. Neural formulations such as Neural Radiance Fields provide high expressivity but require costly ray marching for rendering, whereas…

We present a new approach for synthesizing novel views of people in new poses. Our novel differentiable renderer enables the synthesis of highly realistic images from any viewpoint. Rather than operating over mesh-based structures, our…

Computer Vision and Pattern Recognition · Computer Science 2022-02-22 Guillaume Rochette , Chris Russell , Richard Bowden

We introduce X-Ray, a novel 3D sequential representation inspired by the penetrability of x-ray scans. X-Ray transforms a 3D object into a series of surface frames at different layers, making it suitable for generating 3D models from…

Computer Vision and Pattern Recognition · Computer Science 2024-06-04 Tao Hu , Wenhang Ge , Yuyang Zhao , Gim Hee Lee

Creation of collision objects for 3D models is a time-consuming task, requiring modelers to manually place primitives such as bounding boxes, capsules, spheres, and other convex primitives to approximate complex meshes. While there has been…

Graphics · Computer Science 2026-02-10 Julian Knodt , Xifeng Gao

Simplified proxy models are commonly used to represent architectural structures, reducing storage requirements and enabling real-time rendering. However, the geometric simplifications inherent in proxies result in a loss of fine color and…

Graphics · Computer Science 2025-10-01 Weidan Xiong , Yongli Wu , Bochuan Zeng , Jianwei Guo , Dani Lischinski , Daniel Cohen-Or , Hui Huang