16 citations · 79 across the 61 of their papers we have counts for
38 papers · 1 filter
OctoSense: Self-Supervised Learning for Multimodal Robot Perception
Anthony Bisulco, Jeremy Wang, Kostas Daniilidis +2
We present OctoSense, an open-source sensor platform with stereo RGB and event cameras, LiDAR, a thermal camera, an inertial measurement unit, RTK-corrected global positioning syst…
VGGT-HPE: Reframing Head Pose Estimation as Relative Pose Prediction
Vasiliki Vasileiou, Panagiotis P. Filntisis, Petros Maragos +1
Monocular head pose estimation is traditionally formulated as direct regression from a single image to an absolute pose. This paradigm forces the network to implicitly internalize…
Match-Any-Events: Zero-Shot Motion-Robust Feature Matching Across Wide Baselines for Event Cameras
Ruijun Zhang, Hang Su, Kostas Daniilidis +1
Event cameras have recently shown promising capabilities in instantaneous motion estimation due to their robustness to low light and fast motions. However, computing wide-baseline…
Electrostatics-Inspired Surface Reconstruction (EISR): Recovering 3D Shapes as a Superposition of Poisson's PDE Solutions
Diego Patiño, Knut Peterson, Kostas Daniilidis +1
Implicit shape representation, such as SDFs, is a popular approach to recover the surface of a 3D shape as the level sets of a scalar field. Several methods approximate SDFs using…
Next Best View Selections for Semantic and Dynamic 3D Gaussian Splatting
Yiqian Li, Wen Jiang, Kostas Daniilidis
Understanding semantics and dynamics has been crucial for embodied agents in various tasks. Both tasks have much more data redundancy than the static scene understanding task. We f…
Zero-shot Reconstruction of In-Scene Object Manipulation from Video
Dixuan Lin, Tianyou Wang, Zhuoyang Pan +3
We build the first system to address the problem of reconstructing in-scene object manipulation from a monocular RGB video. It is challenging due to ill-posed scene reconstruction,…
DIMO: Diverse 3D Motion Generation for Arbitrary Objects
Linzhan Mou, Jiahui Lei, Chen Wang +2
We present DIMO, a generative approach capable of generating diverse 3D motions for arbitrary objects from a single image. The core idea of our work is to leverage the rich priors…
Fast Feature Field (): A Predictive Representation of Events
Richeek Das, Kostas Daniilidis, Pratik Chaudhari
This paper develops a mathematical argument and algorithms for building representations of data from event-based cameras, that we call Fast Feature Field (). We learn t…
StereoDiff: Stereo-Diffusion Synergy for Video Depth Estimation
Haodong Li, Chen Wang, Jiahui Lei +2
Recent video depth estimation methods achieve great performance by following the paradigm of image depth estimation, i.e., typically fine-tuning pre-trained video diffusion models…
PromptHMR: Promptable Human Mesh Recovery
Yufu Wang, Yu Sun, Priyanka Patel +3
Human pose and shape (HPS) estimation presents challenges in diverse scenarios such as crowded scenes, person-person interactions, and single-view reconstruction. Existing approach…
Zero-1-to-G: Taming Pretrained 2D Diffusion Model for Direct 3D Generation
Xuyi Meng, Chen Wang, Jiahui Lei +3
Recent advances in 2D image generation have achieved remarkable quality,largely driven by the capacity of diffusion models and the availability of large-scale datasets. However, di…
HDGS: Textured 2D Gaussian Splatting for Enhanced Scene Rendering
Yunzhou Song, Heguang Lin, Jiahui Lei +2
Recent advancements in neural rendering, particularly 2D Gaussian Splatting (2DGS), have shown promising results for jointly reconstructing fine appearance and geometry by leveragi…
Continuous-Time Human Motion Field from Events
Ziyun Wang, Ruijun Zhang, Zi-Yan Liu +2
This paper addresses the challenges of estimating a continuous-time human motion field from a stream of events. Existing Human Mesh Recovery (HMR) methods rely predominantly on fra…
ETAP: Event-based Tracking of Any Point
Friedhelm Hamann, Daniel Gehrig, Filbert Febryanto +2
Tracking any point (TAP) recently shifted the motion estimation paradigm from focusing on individual salient points with local templates to tracking arbitrary points with global im…
Equivariant Ray Embeddings for Implicit Multi-View Depth Estimation
Yinshuang Xu, Dian Chen, Katherine Liu +4
Incorporating inductive bias by embedding geometric entities (such as rays) as input has proven successful in multi-view learning. However, the methods adopting this technique typi…
Recent Event Camera Innovations: A Survey
Bharatesh Chakravarthi, Aayush Atul Verma, Kostas Daniilidis +2
Event-based vision, inspired by the human visual system, offers transformative capabilities such as low latency, high dynamic range, and reduced power consumption. This paper prese…
BiEquiFormer: Bi-Equivariant Representations for Global Point Cloud Registration
Stefanos Pertigkiozoglou, Evangelos Chatzipantazis, Kostas Daniilidis
The goal of this paper is to address the problem of global point cloud registration (PCR) i.e., finding the optimal alignment between point clouds irrespective of the initial poses…
Motion-prior Contrast Maximization for Dense Continuous-Time Motion Estimation
Friedhelm Hamann, Ziyun Wang, Ioannis Asmanis +3
Current optical flow and point-tracking methods rely heavily on synthetic datasets. Event cameras are novel vision sensors with advantages in challenging visual conditions, but sta…
Many Perception Tasks are Highly Redundant Functions of their Input Data
Rahul Ramesh, Anthony Bisulco, Ronald W. DiTullio +4
We show that many perception tasks, from visual recognition, semantic segmentation, optical flow, depth estimation to vocalization discrimination, are highly redundant functions of…
MoSca: Dynamic Gaussian Fusion from Casual Videos via 4D Motion Scaffolds
Jiahui Lei, Yijia Weng, Adam Harley +2
We introduce 4D Motion Scaffolds (MoSca), a modern 4D reconstruction system designed to reconstruct and synthesize novel views of dynamic scenes from monocular videos captured casu…
Track Everything Everywhere Fast and Robustly
Yunzhou Song, Jiahui Lei, Ziyun Wang +2
We propose a novel test-time optimization approach for efficiently and robustly tracking any pixel at any time in a video. The latest state-of-the-art optimization-based tracking t…
TRAM: Global Trajectory and Motion of 3D Humans from in-the-wild Videos
Yufu Wang, Ziyun Wang, Lingjie Liu +1
We propose TRAM, a two-stage method to reconstruct a human's global trajectory and motion from in-the-wild videos. TRAM robustifies SLAM to recover the camera motion in the presenc…
Un-EVIMO: Unsupervised Event-Based Independent Motion Segmentation
Ziyun Wang, Jinyuan Guo, Kostas Daniilidis
Event cameras are a novel type of biologically inspired vision sensor known for their high temporal resolution, high dynamic range, and low power consumption. Because of these prop…
Event-based Continuous Color Video Decompression from Single Frames
Ziyun Wang, Friedhelm Hamann, Kenneth Chaney +3
We present ContinuityCam, a novel approach to generate a continuous video from a single static RGB image and an event camera stream. Conventional cameras struggle with high-speed m…