36 citations · 240 across the 46 of their papers we have counts for
55 papers
Self-Supervised Learning of Semantically Consistent Visual Features via a Simple 3D Prior
Sebastian Day, Oisin Mac Aodha
Visual features extracted from vision models like DINOv2 or Stable Diffusion enable high quality semantic correspondence between images. However, such features exhibit documented l…
BAT3R: Bootstrapping Articulated 3D Reconstruction from 2D Image Collections
Jakub Zadrozny, Oisin Mac Aodha, Hakan Bilen
3D reconstruction of articulated objects from a single image is challenging because large training datasets with paired image and 3D supervision are difficult to obtain. Recent poi…
BiMotion: B-spline Motion for Text-guided Dynamic 3D Character Generation
Miaowei Wang, Qingxuan Yan, Zhi Cao +4
Text-guided dynamic 3D character generation has advanced rapidly, yet producing high-quality motion that faithfully reflects rich textual descriptions remains challenging. Existing…
View-Consistent Diffusion Representations for 3D-Consistent Video Generation
Duolikun Danier, Ge Gao, Steven McDonagh +3
Video generation models have made significant progress in generating realistic content, enabling applications in simulation, gaming, and film making. However, current generated vid…
Attentive Feature Aggregation or: How Policies Learn to Stop Worrying about Robustness and Attend to Task-Relevant Visual Cues
Nikolaos Tsagkas, Andreas Sochopoulos, Duolikun Danier +4
The adoption of pre-trained visual representations (PVRs), leveraging features from large-scale vision models, has become a popular paradigm for training visuomotor policies. Howev…
VesselSDF: Distance Field Priors for Vascular Network Reconstruction
Salvatore Esposito, Daniel Rebain, Arno Onken +2
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…
Jamais Vu: Exposing the Generalization Gap in Supervised Semantic Correspondence
Octave Mariotti, Zhipeng Du, Yash Bhalgat +2
Semantic correspondence (SC) aims to establish semantically meaningful matches across different instances of an object category. We illustrate how recent supervised SC methods rema…
Representational Difference Explanations
Neehar Kondapaneni, Oisin Mac Aodha, Pietro Perona
We propose a method for discovering and visualizing the differences between two learned representations, enabling more direct and interpretable model comparisons. We validate our m…
Representational Similarity via Interpretable Visual Concepts
Neehar Kondapaneni, Oisin Mac Aodha, Pietro Perona
How do two deep neural networks differ in how they arrive at a decision? Measuring the similarity of deep networks has been a long-standing open question. Most existing methods pro…
The Temporal Trap: Entanglement in Pre-Trained Visual Representations for Visuomotor Policy Learning
Nikolaos Tsagkas, Andreas Sochopoulos, Duolikun Danier +2
The integration of pre-trained visual representations (PVRs) has significantly advanced visuomotor policy learning. However, effectively leveraging these models remains a challenge…
CrossSDF: 3D Reconstruction of Thin Structures From Cross-Sections
Thomas Walker, Salvatore Esposito, Daniel Rebain +4
Reconstructing complex structures from planar cross-sections is a challenging problem, with wide-reaching applications in medical imaging, manufacturing, and topography. Out-of-the…
DepthCues: Evaluating Monocular Depth Perception in Large Vision Models
Duolikun Danier, Mehmet Aygün, Changjian Li +2
Large-scale pre-trained vision models are becoming increasingly prevalent, offering expressive and generalizable visual representations that benefit various downstream tasks. Recen…
Labeled Data Selection for Category Discovery
Bingchen Zhao, Nico Lang, Serge Belongie +1
Category discovery methods aim to find novel categories in unlabeled visual data. At training time, a set of labeled and unlabeled images are provided, where the labels correspond…
GeoGen: Geometry-Aware Generative Modeling via Signed Distance Functions
Salvatore Esposito, Qingshan Xu, Kacper Kania +6
We introduce a new generative approach for synthesizing 3D geometry and images from single-view collections. Most existing approaches predict volumetric density to render multi-vie…
AirPlanes: Accurate Plane Estimation via 3D-Consistent Embeddings
Jamie Watson, Filippo Aleotti, Mohamed Sayed +5
Extracting planes from a 3D scene is useful for downstream tasks in robotics and augmented reality. In this paper we tackle the problem of estimating the planar surfaces in a scene…
Enhancing 2D Representation Learning with a 3D Prior
Mehmet Aygün, Prithviraj Dhar, Zhicheng Yan +2
Learning robust and effective representations of visual data is a fundamental task in computer vision. Traditionally, this is achieved by training models with labeled data which ca…
Click to Grasp: Zero-Shot Precise Manipulation via Visual Diffusion Descriptors
Nikolaos Tsagkas, Jack Rome, Subramanian Ramamoorthy +2
Precise manipulation that is generalizable across scenes and objects remains a persistent challenge in robotics. Current approaches for this task heavily depend on having a signifi…
Improving Semantic Correspondence with Viewpoint-Guided Spherical Maps
Octave Mariotti, Oisin Mac Aodha, Hakan Bilen
Recent progress in self-supervised representation learning has resulted in models that are capable of extracting image features that are not only effective at encoding image level,…
Active Learning-Based Species Range Estimation
Christian Lange, Elijah Cole, Grant Van Horn +1
We propose a new active learning approach for efficiently estimating the geographic range of a species from a limited number of on the ground observations. We model the range of an…
Whombat: An open-source annotation tool for machine learning development in bioacoustics
Santiago Martinez Balvanera, Oisin Mac Aodha, Matthew J. Weldy +3
1. Automated analysis of bioacoustic recordings using machine learning (ML) methods has the potential to greatly scale biodiversity monitoring efforts. The use of ML for high-stake…
Spatial Implicit Neural Representations for Global-Scale Species Mapping
Elijah Cole, Grant Van Horn, Christian Lange +5
Estimating the geographical range of a species from sparse observations is a challenging and important geospatial prediction problem. Given a set of locations where a species has b…
VL-Fields: Towards Language-Grounded Neural Implicit Spatial Representations
Nikolaos Tsagkas, Oisin Mac Aodha, Chris Xiaoxuan Lu
We present Visual-Language Fields (VL-Fields), a neural implicit spatial representation that enables open-vocabulary semantic queries. Our model encodes and fuses the geometry of a…
Virtual Occlusions Through Implicit Depth
Jamie Watson, Mohamed Sayed, Zawar Qureshi +4
For augmented reality (AR), it is important that virtual assets appear to `sit among' real world objects. The virtual element should variously occlude and be occluded by real matte…
Incremental Generalized Category Discovery
Bingchen Zhao, Oisin Mac Aodha
We explore the problem of Incremental Generalized Category Discovery (IGCD). This is a challenging category incremental learning setting where the goal is to develop models that ca…