8 citations · 33 across the 29 of their papers we have counts for
29 papers
OmniShape: Zero-Shot Multi-Hypothesis Shape and Pose Estimation in the Real World
Katherine Liu, Sergey Zakharov, Dian Chen +4
We would like to estimate the pose and full shape of an object from a single observation, without assuming known 3D model or category. In this work, we propose OmniShape, the first…
Streaming Detection of Queried Event Start
Cristobal Eyzaguirre, Eric Tang, Shyamal Buch +3
Robotics, autonomous driving, augmented reality, and many embodied computer vision applications must quickly react to user-defined events unfolding in real time. We address this se…
ReFiNe: Recursive Field Networks for Cross-modal Multi-scene Representation
Sergey Zakharov, Katherine Liu, Adrien Gaidon +1
The common trade-offs of state-of-the-art methods for multi-shape representation (a single model "packing" multiple objects) involve trading modeling accuracy against memory and st…
Linearizing Large Language Models
Jean Mercat, Igor Vasiljevic, Sedrick Keh +4
Linear transformers have emerged as a subquadratic-time alternative to softmax attention and have garnered significant interest due to their fixed-size recurrent state that lowers…
NeRF-MAE: Masked AutoEncoders for Self-Supervised 3D Representation Learning for Neural Radiance Fields
Muhammad Zubair Irshad, Sergey Zakharov, Vitor Guizilini +3
Neural fields excel in computer vision and robotics due to their ability to understand the 3D visual world such as inferring semantics, geometry, and dynamics. Given the capabiliti…
Zero-Shot Multi-Object Scene Completion
Shun Iwase, Katherine Liu, Vitor Guizilini +4
We present a 3D scene completion method that recovers the complete geometry of multiple unseen objects in complex scenes from a single RGB-D image. Despite notable advancements in…
Understanding Video Transformers via Universal Concept Discovery
Matthew Kowal, Achal Dave, Rares Ambrus +3
This paper studies the problem of concept-based interpretability of transformer representations for videos. Concretely, we seek to explain the decision-making process of video tran…
NeO 360: Neural Fields for Sparse View Synthesis of Outdoor Scenes
Muhammad Zubair Irshad, Sergey Zakharov, Katherine Liu +5
Recent implicit neural representations have shown great results for novel view synthesis. However, existing methods require expensive per-scene optimization from many views hence l…
Robust Self-Supervised Extrinsic Self-Calibration
Takayuki Kanai, Igor Vasiljevic, Vitor Guizilini +2
Autonomous vehicles and robots need to operate over a wide variety of scenarios in order to complete tasks efficiently and safely. Multi-camera self-supervised monocular depth esti…
Towards Zero-Shot Scale-Aware Monocular Depth Estimation
Vitor Guizilini, Igor Vasiljevic, Dian Chen +2
Monocular depth estimation is scale-ambiguous, and thus requires scale supervision to produce metric predictions. Even so, the resulting models will be geometry-specific, with lear…
Multi-Object Manipulation via Object-Centric Neural Scattering Functions
Stephen Tian, Yancheng Cai, Hong-Xing Yu +5
Learned visual dynamics models have proven effective for robotic manipulation tasks. Yet, it remains unclear how best to represent scenes involving multi-object interactions. Curre…
HomE: Homography-Equivariant Video Representation Learning
Anirudh Sriram, Adrien Gaidon, Jiajun Wu +3
Recent advances in self-supervised representation learning have enabled more efficient and robust model performance without relying on extensive labeled data. However, most works a…
NeRFuser: Large-Scale Scene Representation by NeRF Fusion
Jiading Fang, Shengjie Lin, Igor Vasiljevic +5
A practical benefit of implicit visual representations like Neural Radiance Fields (NeRFs) is their memory efficiency: large scenes can be efficiently stored and shared as small ne…
Viewpoint Equivariance for Multi-View 3D Object Detection
Dian Chen, Jie Li, Vitor Guizilini +2
3D object detection from visual sensors is a cornerstone capability of robotic systems. State-of-the-art methods focus on reasoning and decoding object bounding boxes from multi-vi…
DeLiRa: Self-Supervised Depth, Light, and Radiance Fields
Vitor Guizilini, Igor Vasiljevic, Jiading Fang +4
Differentiable volumetric rendering is a powerful paradigm for 3D reconstruction and novel view synthesis. However, standard volume rendering approaches struggle with degenerate ge…
Object Discovery from Motion-Guided Tokens
Zhipeng Bao, Pavel Tokmakov, Yu-Xiong Wang +2
Object discovery -- separating objects from the background without manual labels -- is a fundamental open challenge in computer vision. Previous methods struggle to go beyond clust…
ROAD: Learning an Implicit Recursive Octree Auto-Decoder to Efficiently Encode 3D Shapes
Sergey Zakharov, Rares Ambrus, Katherine Liu +1
Compact and accurate representations of 3D shapes are central to many perception and robotics tasks. State-of-the-art learning-based methods can reconstruct single objects but scal…
Breaking the "Object" in Video Object Segmentation
Pavel Tokmakov, Jie Li, Adrien Gaidon
The appearance of an object can be fleeting when it transforms. As eggs are broken or paper is torn, their color, shape and texture can change dramatically, preserving virtually no…
Photo-realistic Neural Domain Randomization
Sergey Zakharov, Rares Ambrus, Vitor Guizilini +2
Synthetic data is a scalable alternative to manual supervision, but it requires overcoming the sim-to-real domain gap. This discrepancy between virtual and real worlds is addressed…
Depth Is All You Need for Monocular 3D Detection
Dennis Park, Jie Li, Dian Chen +2
A key contributor to recent progress in 3D detection from single images is monocular depth estimation. Existing methods focus on how to leverage depth explicitly, by generating pse…
Depth Field Networks for Generalizable Multi-view Scene Representation
Vitor Guizilini, Igor Vasiljevic, Jiading Fang +4
Modern 3D computer vision leverages learning to boost geometric reasoning, mapping image data to classical structures such as cost volumes or epipolar constraints to improve matchi…
ShAPO: Implicit Representations for Multi-Object Shape, Appearance, and Pose Optimization
Muhammad Zubair Irshad, Sergey Zakharov, Rares Ambrus +3
Our method studies the complex task of object-centric 3D understanding from a single RGB-D observation. As it is an ill-posed problem, existing methods suffer from low performance…
Neural Groundplans: Persistent Neural Scene Representations from a Single Image
Prafull Sharma, Ayush Tewari, Yilun Du +7
We present a method to map 2D image observations of a scene to a persistent 3D scene representation, enabling novel view synthesis and disentangled representation of the movable an…
Revisiting the "Video" in Video-Language Understanding
Shyamal Buch, Cristóbal Eyzaguirre, Adrien Gaidon +3
What makes a video task uniquely suited for videos, beyond what can be understood from a single image? Building on recent progress in self-supervised image-language models, we revi…