Related papers: Learning 3D Representations for Spatial Intelligen…
Recent advances in Gaussian Splatting based 3D scene representation have shown two major trends: semantics-oriented approaches that focus on high-level understanding but lack explicit 3D geometry modeling, and structure-oriented approaches…
Recent studies have shown remarkable advances in 3D human pose estimation from monocular images, with the help of large-scale in-door 3D datasets and sophisticated network architectures. However, the generalizability to different…
Representing visual signals by implicit representation (e.g., a coordinate based deep network) has prevailed among many vision tasks. This work explores a new intriguing direction: training a stylized implicit representation, using a…
Recent advancements in Generalizable Gaussian Splatting have enabled robust 3D reconstruction from sparse input views by utilizing feed-forward Gaussian Splatting models, achieving superior cross-scene generalization. However, while many…
Neural implicit representations, including Neural Distance Fields and Neural Radiance Fields, have demonstrated significant capabilities for reconstructing surfaces with complicated geometry and topology, and generating novel views of a…
The question of representation of 3D geometry is of vital importance when it comes to leveraging the recent advances in the field of machine learning for geometry processing tasks. For common unstructured surface meshes state-of-the-art…
The scale diversity of point cloud data presents significant challenges in developing unified representation learning techniques for 3D vision. Currently, there are few unified 3D models, and no existing pre-training method is equally…
Semantic-aware 3D reconstruction from sparse, unposed images remains challenging for feed-forward 3D Gaussian Splatting (3DGS). Existing methods often predict an over-complete set of Gaussian primitives under sparse-view supervision,…
3D scene reconstruction from 2D images has been a long-standing task. Instead of estimating per-frame depth maps and fusing them in 3D, recent research leverages the neural implicit surface as a unified representation for 3D reconstruction.…
Unified remote sensing multimodal models exhibit a pronounced spatial reversal curse: Although they can accurately recognize and describe object locations in images, they often fail to faithfully execute the same spatial relations during…
Reconstructing object deformation from a single image remains a significant challenge in computer vision and graphics. Existing methods typically rely on multi-view video to recover deformation, limiting their applicability under…
Implicit neural representation has paved the way for new approaches to dynamic scene reconstruction and rendering. Nonetheless, cutting-edge dynamic neural rendering methods rely heavily on these implicit representations, which frequently…
Recently, multi-view diffusion-based 3D generation methods have gained significant attention. However, these methods often suffer from shape and texture misalignment across generated multi-view images, leading to low-quality 3D generation…
Self-supervised learning (SSL) for point cloud pre-training has become a cornerstone for many 3D vision tasks, enabling effective learning from large-scale unannotated data. At the scene level, existing SSL methods often incorporate volume…
Joint rendering and deformation of mesh and 3D Gaussian Splatting (3DGS) have significant value as both representa tions offer complementary advantages for graphics applica tions. However, due to differences in representation and ren dering…
We introduce a novel learning-based method for encoding and manipulating 3D surface meshes. Our method is specifically designed to create an interpretable embedding space for deformable shape collections. Unlike previous 3D mesh…
Feedforward 3D Gaussian Splatting (3DGS) overcomes the limitations of optimization-based 3DGS by enabling fast and high-quality reconstruction without the need for per-scene optimization. However, existing feedforward approaches typically…
We have introduced SegSplat, a novel framework designed to bridge the gap between rapid, feed-forward 3D reconstruction and rich, open-vocabulary semantic understanding. By constructing a compact semantic memory bank from multi-view 2D…
Implicit 3D surface reconstruction of an object from its partial and noisy 3D point cloud scan is the classical geometry processing and 3D computer vision problem. In the literature, various 3D shape representations have been developed,…
Generalizable 3D Gaussian Splatting reconstruction showcases advanced Image-to-3D content creation but requires substantial computational resources and large datasets, posing challenges to training models from scratch. Current methods…