Related papers: Visual Geometry Grounded Deep Structure From Motio…

We study the problem of applying 3D Foundation Models (3DFMs) to dense Novel View Synthesis (NVS). Despite significant progress in Novel View Synthesis powered by NeRF and 3DGS, current approaches remain reliant on accurate 3D attributes…

Video semantic segmentation aims to generate accurate semantic maps for each video frame. To this end, many works dedicate to integrate diverse information from consecutive frames to enhance the features for prediction, where a feature…

Visual localization techniques rely upon some underlying scene representation to localize against. These representations can be explicit such as 3D SFM map or implicit, such as a neural network that learns to encode the scene. The former…

Traditional SLAM systems, which rely on bundle adjustment, struggle with highly dynamic scenes commonly found in casual videos. Such videos entangle the motion of dynamic elements, undermining the assumption of static environments required…

Video segmentation -- partitioning video frames into multiple segments or objects -- plays a critical role in a broad range of practical applications, from enhancing visual effects in movie, to understanding scenes in autonomous driving, to…

We present a novel 3D mapping pipeline for large-scale indoor environments. To address the significant challenges in large-scale indoor scenes, such as prevalent occlusions and textureless regions, we propose IM360, a novel approach that…

Accurate segmentation of vascular networks from sparse CT scan slices remains a significant challenge in medical imaging, particularly due to the thin, branching nature of vessels and the inherent sparsity between imaging planes. Existing…

Usual Structure-from-Motion (SfM) techniques require at least trifocal overlaps to calibrate cameras and reconstruct a scene. We consider here scenarios of reduced image sets with little overlap, possibly as low as two images at most seeing…

Visual localization has traditionally been formulated as a pair-wise pose regression problem. Existing approaches mainly estimate relative poses between two images and employ a late-fusion strategy to obtain absolute pose estimates.…

Reconstructing coherent 3D geometry and appearance from unposed multi-view images is a fundamental yet challenging problem in computer vision. Most existing visual geometry foundation models predict explicit geometry by regressing…

Reconstructing 3D vehicles from noisy and sparse partial point clouds is of great significance to autonomous driving. Most existing 3D reconstruction methods cannot be directly applied to this problem because they are elaborately designed…

Recent advances in neural reconstruction enable high-quality 3D object reconstruction from casually captured image collections. Current techniques mostly analyze their progress on relatively simple image collections where…

We describe a set of tools for analyzing, visualizing, and assessing architectural/construction progress with unordered photo collections and 3D building models. With our interface, a user guides the registration of the model in one of the…

While weakly supervised multi-view face reconstruction (MVR) is garnering increased attention, one critical issue still remains open: how to effectively interact and fuse multiple image information to reconstruct high-precision 3D models.…

Generating high-dimensional visual modalities is a computationally intensive task. A common solution is progressive generation, where the outputs are synthesized in a coarse-to-fine spectral autoregressive manner. While diffusion models…

We present a novel fruit counting pipeline that combines deep segmentation, frame to frame tracking, and 3D localization to accurately count visible fruits across a sequence of images. Our pipeline works on image streams from a monocular…

Single-view depth estimation (SVDE) plays a crucial role in scene understanding for AR applications, 3D modeling, and robotics, providing the geometry of a scene based on a single image. Recent works have shown that a successful solution…

Effective scene representation is critical for the visual grounding ability of representations, yet existing methods for 3D Visual Grounding are often constrained. They either only focus on geometric and visual cues, or, like traditional 3D…

Reconstructing dynamic 4D scenes is an important yet challenging task. While 3D foundation models like VGGT excel in static settings, they often struggle with dynamic sequences where motion causes significant geometric ambiguity. To address…

Reconstructing dynamic 4D scenes is challenging, as it requires robust disentanglement of dynamic objects from the static background. While 3D foundation models like VGGT provide accurate 3D geometry, their performance drops markedly when…