7 citations · 7 across the 14 of their papers we have counts for
21 papers
Beyond Adjacent Layers: Graph-Guided Layer Fusion for Compressing Large Language Models
Muhammad Usama, Yeoreum Jung
Existing depth-compression methods for large language models (LLMs) score layers individually or group only adjacent or contiguous layers, implicitly assuming that functional redun…
HexVIO: Towards All-Day Stereo-Inertial Tracking Through Commodity DSPs
Patrick Wolf, Mateo de Mayo, Daniel Cremers
The ability of a device to localize itself within its surroundings is a fundamental prerequisite for spatial computing. Visual-inertial odometry (VIO) has proven to be a cost-effec…
ORMA: Optimization-based Monocular 4D Reconstruction of Articulated Animals
Xuyi Hu, Francesco Palandra, Shangzhe Wu +3
Recovering articulated 4D representations of animals from monocular videos remains challenging due to the large diversity of quadruped morphologies and lack of animal 4D supervisio…
VkVIO: Cross-platform GPU Acceleration for Visual-Inertial Odometry with Vulkan
Ole Hoffmann, Mateo de Mayo, Daniel Cremers
Perception in robotics and XR fundamentally relies on good state estimation. Visual-inertial odometry (VIO) and Simultaneous Localization and Mapping (VI-SLAM) are proven ways of a…
Elastic Triangle Splatting
Tian Shi, Shenhan Qian, Daniel Cremers
While neural rendering methods such as 3D Gaussian Splatting achieve remarkable visual fidelity, traditional polygonal meshes remain the backbone of established graphics pipelines.…
Stipple: Real-Time Incremental Gaussian Splatting with Visual-Inertial Tracking
Kilian Northoff, Mateo de Mayo, Daniel Cremers
3D Gaussian Splatting (3DGS) provides efficient rendering of photo-realistic scenes, but its heavy preprocessing and training steps make it a poor fit for applications that require…
OrthoTrack: Continuous 6-DoF UAV Trajectory Estimation Anchored in Public Orthophotos
Oussema Dhaouadi, Zuria Bauer, Johannes Michael Meier +3
Continuous 6-DoF pose estimation is essential for autonomous UAV operations. Yet, existing visual odometry and SLAM methods accumulate drift and yield only relative, up-to-scale tr…
Robot Self-Improvement via Human-Video Dynamics Models
Hanzhi Chen, Anran Zhang, Simon Schaefer +5
A central question in robot learning is how to acquire skills from the kinds of data that humans learn from: passive observation, embodied practice, and the experience of failure.…
DynaTok: Token-Based 4D Reconstruction from Partial Point Clouds
Weirong Chen, Keisuke Tateno, Hidenobu Matsuki +3
We address 4D reconstruction from partial point cloud sequences, where depth-sensor observations are incomplete, unordered, and lack explicit temporal correspondences. This geometr…
BA-T: An Iterative Transformer for Two-View Bundle Adjustment
Ganlin Zhang, Weirong Chen, Daniel Cremers +1
Feed-forward models for 3D reconstruction have achieved strong performance using deep cross-view attention to exchange information across images. However, these approaches often de…
VisDom: Sparse Novel View Synthesis with Visible Domain Constraint
Mariia Gladkova, Tarun Yenamandra, Edmond Boyer +3
Sparse novel view synthesis (NVS) remains challenging due to the ambiguity of recovering 3D geometry from few input views. While NeRF- and Gaussian Splatting (GS)-based methods per…
EgoFlow: Gradient-Guided Flow Matching for Egocentric 6DoF Object Motion Generation
Abhishek Saroha, Huajian Zeng, Xingxing Zuo +2
Understanding and predicting object motion from egocentric video is fundamental to embodied perception and interaction. However, generating physically consistent 6DoF trajectories…
Non-Rigid 3D Shape Correspondences: From Foundations to Open Challenges and Opportunities
Aleksei Zhuravlev, Lennart Bastian, Dongliang Cao +12
Estimating correspondences between deformed shape instances is a long-standing problem in computer graphics; numerous applications, from texture transfer to statistical modelling,…
NOVA3R: Non-pixel-aligned Visual Transformer for Amodal 3D Reconstruction
Weirong Chen, Chuanxia Zheng, Ganlin Zhang +2
We present NOVA3R, an effective approach for non-pixel-aligned 3D reconstruction from a set of unposed images in a feed-forward manner. Unlike pixel-aligned methods that tie geomet…
Flow4R: Unifying 4D Reconstruction and Tracking with Scene Flow
Shenhan Qian, Ganlin Zhang, Shangzhe Wu +1
Reconstructing and tracking dynamic 3D scenes is a fundamental challenge in computer vision. Existing methods typically decouple geometry from motion: static multi-view reconstruct…
ViSTA-SLAM: Visual SLAM with Symmetric Two-view Association
Ganlin Zhang, Shenhan Qian, Xi Wang +1
We present ViSTA-SLAM as a real-time monocular visual SLAM system that operates without requiring camera intrinsics, making it broadly applicable across diverse camera setups. At i…
ProBA: Probabilistic Bundle Adjustment with the Bhattacharyya Coefficient
Jason Chui, Hector Andrade-Loarca, Daniel Cremers
Classical Bundle Adjustment (BA) is fundamentally limited by its reliance on precise metric initialization and prior camera intrinsics. While modern dense matchers offer high-fidel…
Back on Track: Bundle Adjustment for Dynamic Scene Reconstruction
Weirong Chen, Ganlin Zhang, Felix Wimbauer +4
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,…
DynSUP: Dynamic Gaussian Splatting from An Unposed Image Pair
Weihang Li, Weirong Chen, Shenhan Qian +3
Recent advances in 3D Gaussian Splatting have shown promising results. Existing methods typically assume static scenes and/or multiple images with prior poses. Dynamics, sparse vie…
PG-SLAM: Photo-realistic and Geometry-aware RGB-D SLAM in Dynamic Environments
Haoang Li, Xiangqi Meng, Xingxing Zuo +3
Simultaneous localization and mapping (SLAM) has achieved impressive performance in static environments. However, SLAM in dynamic environments remains an open question. Many method…
HI-SLAM2: Geometry-Aware Gaussian SLAM for Fast Monocular Scene Reconstruction
Wei Zhang, Qing Cheng, David Skuddis +3
We present HI-SLAM2, a geometry-aware Gaussian SLAM system that achieves fast and accurate monocular scene reconstruction using only RGB input. Existing Neural SLAM or 3DGS-based S…