English
Related papers

Related papers: VGG-T$^3$: Offline Feed-Forward 3D Reconstruction …

200 papers

Recent advances in novel view synthesis (NVS) have enabled real-time rendering with 3D Gaussian Splatting (3DGS). However, existing methods struggle with artifacts and missing regions when rendering from viewpoints that deviate from the…

Computer Vision and Pattern Recognition · Computer Science 2025-08-11 Minsu Kim , Subin Jeon , In Cho , Mijin Yoo , Seon Joo Kim

Video tokenization procedure is critical for a wide range of video processing tasks. Most existing approaches directly transform video into fixed-grid and patch-wise tokens, which exhibit limited versatility. Spatially, uniformly allocating…

Computer Vision and Pattern Recognition · Computer Science 2025-08-18 Zhenghao Chen , Zicong Chen , Lei Liu , Yiming Wu , Dong Xu

With recent advances, Feed-forward Reconstruction Models (FFRMs) have demonstrated great potential in reconstruction quality and adaptiveness to multiple downstream tasks. However, the excessive reliance on multi-view geometric annotations,…

Computer Vision and Pattern Recognition · Computer Science 2026-04-02 Youyu Chen , Junjun Jiang , Yueru Luo , Kui Jiang , Xianming Liu , Xu Yan , Dave Zhenyu Chen

Video Temporal Grounding (VTG), the task of localizing video segments from text queries, struggles in open-world settings due to limited dataset scale and semantic diversity, causing performance gaps between common and rare concepts. To…

Computer Vision and Pattern Recognition · Computer Science 2026-04-29 Minghang Zheng , Zihao Yin , Yi Yang , Yuxin Peng , Yang Liu

This paper presents a novel method for building scalable 3D generative models utilizing pre-trained video diffusion models. The primary obstacle in developing foundation 3D generative models is the limited availability of 3D data. Unlike…

Computer Vision and Pattern Recognition · Computer Science 2024-07-22 Junlin Han , Filippos Kokkinos , Philip Torr

Streaming 3D perception is well suited to robotics and augmented reality, where long visual streams must be processed efficiently and consistently. Recent recurrent models offer a promising solution by maintaining fixed-size states and…

Computer Vision and Pattern Recognition · Computer Science 2026-04-09 Changkun Liu , Jiezhi Yang , Zeman Li , Yuan Deng , Jiancong Guo , Luca Ballan

3D Visual Grounding (3DVG) aims to locate objects in 3D scenes based on textual descriptions, essential for applications like augmented reality and robotics. Traditional 3DVG approaches rely on annotated 3D datasets and predefined object…

Computer Vision and Pattern Recognition · Computer Science 2025-05-30 Rong Li , Shijie Li , Lingdong Kong , Xulei Yang , Junwei Liang

Recent developments in Multimodal Large Language Models (MLLMs) have significantly improved Vision-Language (VL) reasoning in 2D domains. However, extending these capabilities to 3D scene understanding remains a major challenge. Existing 3D…

Computer Vision and Pattern Recognition · Computer Science 2026-03-03 Haijier Chen , Bo Xu , Shoujian Zhang , Haoze Liu , Jiaxuan Lin , Jingrong Wang

We present an out-of-core variational approach for surface reconstruction from a set of aligned depth maps. Input depth maps are supposed to be reconstructed from regular photos or/and can be a representation of terrestrial LIDAR point…

Computer Vision and Pattern Recognition · Computer Science 2021-08-17 Nikolai Poliarnyi

Current 3D reconstruction techniques struggle to infer unbounded scenes from a few images faithfully. Specifically, existing methods have high computational demands, require detailed pose information, and cannot reconstruct occluded regions…

Computer Vision and Pattern Recognition · Computer Science 2025-04-08 Théo Gieruc , Marius Kästingschäfer , Sebastian Bernhard , Mathieu Salzmann

3D reconstruction of dynamic scenes is a long-standing problem in computer graphics and increasingly difficult the less information is available. Shape-from-Template (SfT) methods aim to reconstruct a template-based geometry from RGB images…

Computer Vision and Pattern Recognition · Computer Science 2024-04-16 David Stotko , Nils Wandel , Reinhard Klein

We propose Long-LRM, a feed-forward 3D Gaussian reconstruction model for instant, high-resolution, 360{\deg} wide-coverage, scene-level reconstruction. Specifically, it takes in 32 input images at a resolution of 960x540 and produces the…

Computer Vision and Pattern Recognition · Computer Science 2025-08-04 Chen Ziwen , Hao Tan , Kai Zhang , Sai Bi , Fujun Luan , Yicong Hong , Li Fuxin , Zexiang Xu

Feed-forward 3D reconstruction models are efficient but rigid: once trained, they perform inference in a zero-shot manner and cannot adapt to the test scene. As a result, visually plausible reconstructions often contain errors, particularly…

Computer Vision and Pattern Recognition · Computer Science 2026-04-16 Yuhang Dai , Xingyi Yang

Streaming Visual Geometry Transformers such as StreamVGGT enable strong online 3D perception, but their KV-cache grows unbounded over long streams, limiting practical deployment. We revisit bounded-memory streaming from the perspective of…

Computer Vision and Pattern Recognition · Computer Science 2026-04-21 Zhisong Xu , Takeshi Oishi

Understanding a 3D scene immediately with its exploration is essential for embodied tasks, where an agent must construct and comprehend the 3D scene in an online and nearly real-time manner. In this study, we propose EmbodiedSplat, an…

Computer Vision and Pattern Recognition · Computer Science 2026-03-05 Seungjun Lee , Zihan Wang , Yunsong Wang , Gim Hee Lee

State-of-the-art methods for large-scale 3D reconstruction from RGB-D sensors usually reduce drift in camera tracking by globally optimizing the estimated camera poses in real-time without simultaneously updating the reconstructed surface…

Computer Vision and Pattern Recognition · Computer Science 2017-09-13 Robert Maier , Raphael Schaller , Daniel Cremers

We present Online3R, a new sequential reconstruction framework that is capable of adapting to new scenes through online learning, effectively resolving inconsistency issues. Specifically, we introduce a set of learnable lightweight visual…

Computer Vision and Pattern Recognition · Computer Science 2026-04-13 Shunkai Zhou , Zike Yan , Fei Xue , Dong Wu , Yuchen Deng , Hongbin Zha

Recently, the integration of the efficient feed-forward scheme into 3D Gaussian Splatting (3DGS) has been actively explored. However, most existing methods focus on sparse view reconstruction of small regions and cannot produce eligible…

Computer Vision and Pattern Recognition · Computer Science 2025-04-01 Yunsong Wang , Tianxin Huang , Hanlin Chen , Gim Hee Lee

Recent advances in 3D Gaussian Splatting (3DGS) present two main directions: feed-forward models offer fast inference in sparse-view settings, while per-scene optimization yields high-quality renderings but is computationally expensive. To…

Computer Vision and Pattern Recognition · Computer Science 2026-04-02 Yueh-Cheng Liu , Jozef Hladký , Matthias Nießner , Angela Dai

Reconstructing high-quality 3D models from sparse 2D images has garnered significant attention in computer vision. Recently, 3D Gaussian Splatting (3DGS) has gained prominence due to its explicit representation with efficient training speed…

Computer Vision and Pattern Recognition · Computer Science 2024-12-31 Keng-Wei Chang , Zi-Ming Wang , Shang-Hong Lai