Transflow: Transformer as flow learner
Optical flow is an indispensable building block for various important computer vision tasks,
including motion estimation, object tracking, and disparity measurement. In this work, we …
including motion estimation, object tracking, and disparity measurement. In this work, we …
Bridging the domain gap: Self-supervised 3d scene understanding with foundation models
Foundation models have achieved remarkable results in 2D and language tasks like image
segmentation, object detection, and visual-language understanding. However, their …
segmentation, object detection, and visual-language understanding. However, their …
Sc-depthv3: Robust self-supervised monocular depth estimation for dynamic scenes
Self-supervised monocular depth estimation has shown impressive results in static scenes. It
relies on the multi-view consistency assumption for training networks, however, that is …
relies on the multi-view consistency assumption for training networks, however, that is …
Learning to fuse monocular and multi-view cues for multi-frame depth estimation in dynamic scenes
Multi-frame depth estimation generally achieves high accuracy relying on the multi-view
geometric consistency. When applied in dynamic scenes, eg, autonomous driving, this …
geometric consistency. When applied in dynamic scenes, eg, autonomous driving, this …
Sqldepth: Generalizable self-supervised fine-structured monocular depth estimation
Recently, self-supervised monocular depth estimation has gained popularity with numerous
applications in autonomous driving and robotics. However, existing solutions primarily seek …
applications in autonomous driving and robotics. However, existing solutions primarily seek …
Naruto: Neural active reconstruction from uncertain target observations
We present NARUTO a neural active reconstruction system that combines a hybrid neural
representation with uncertainty learning enabling high-fidelity surface reconstruction. Our …
representation with uncertainty learning enabling high-fidelity surface reconstruction. Our …
CVRecon: Rethinking 3d geometric feature learning for neural reconstruction
Recent advances in neural reconstruction using posed image sequences have made
remarkable progress. However, due to the lack of depth information, existing volumetric …
remarkable progress. However, due to the lack of depth information, existing volumetric …
Know Your Neighbors: Improving Single-View Reconstruction via Spatial Vision-Language Reasoning
Recovering the 3D scene geometry from a single view is a fundamental yet ill-posed
problem in computer vision. While classical depth estimation methods infer only a 2.5 D …
problem in computer vision. While classical depth estimation methods infer only a 2.5 D …
[PDF][PDF] Deflowslam: Self-supervised scene motion decomposition for dynamic dense slam
We present a novel dual-flow representation of scene motion that decomposes the optical
flow into a static flow field caused by the camera motion and another dynamic flow field …
flow into a static flow field caused by the camera motion and another dynamic flow field …
Ds-depth: Dynamic and static depth estimation via a fusion cost volume
Self-supervised monocular depth estimation methods typically rely on the reprojection error
to capture geometric relationships between successive frames in static environments …
to capture geometric relationships between successive frames in static environments …