research
∙
09/12/2023
Language Models as Black-Box Optimizers for Vision-Language Models
Vision-language models (VLMs) pre-trained on web-scale datasets have dem...
share
research
∙
08/18/2023
Dynamic 3D Gaussians: Tracking by Persistent Dynamic View Synthesis
We present a method that simultaneously addresses the tasks of dynamic s...
research
∙
08/17/2023
Learning Lightweight Object Detectors via Multi-Teacher Progressive Distillation
Resource-constrained perception systems such as edge computing and visio...
research
∙
08/08/2023
An Empirical Analysis of Range for 3D Object Detection
LiDAR-based 3D detection plays a vital role in autonomous navigation. Su...
research
∙
06/24/2023
Thinking Like an Annotator: Generation of Dataset Labeling Instructions
Large-scale datasets are essential to modern day deep learning. Advocate...
research
∙
06/02/2023
VisualGPTScore: Visio-Linguistic Reasoning with Multimodal Generative Pre-Training Scores
Vision-language models (VLMs) discriminatively pre-trained with contrast...
research
∙
05/12/2023
WEDGE: A multi-weather autonomous driving dataset built from generative vision-language models
The open road poses many challenges to autonomous perception, including ...
research
∙
05/10/2023
Reconstructing Animatable Categories from Videos
Building animatable 3D models is challenging due to the need for 3D scan...
research
∙
05/10/2023
Joint Metrics Matter: A Better Standard for Trajectory Forecasting
Multi-modal trajectory forecasting methods commonly evaluate using singl...
research
∙
05/08/2023
RelPose++: Recovering 6D Poses from Sparse-view Observations
We address the task of estimating 6D camera poses from sparse-view image...
research
∙
04/27/2023
SLoMo: A General System for Legged Robot Motion Imitation from Casual Videos
We present SLoMo: a first-of-its-kind framework for transferring skilled...
research
∙
04/24/2023
Total-Recon: Deformable Scene Reconstruction for Embodied View Synthesis
We explore the task of embodied view synthesis from monocular videos of ...
research
∙
04/04/2023
Re-Evaluating LiDAR Scene Flow for Autonomous Driving
Current methods for self-supervised LiDAR scene flow estimation work poo...
research
∙
03/27/2023
Learning to Zoom and Unzoom
Many perception systems in mobile computing, autonomous navigation, and ...
research
∙
03/25/2023
SUDS: Scalable Urban Dynamic Scenes
We extend neural radiance fields (NeRFs) to dynamic large-scale urban sc...
research
∙
02/25/2023
Point Cloud Forecasting as a Proxy for 4D Occupancy Forecasting
Predicting how the world can evolve in the future is crucial for motion ...
research
∙
02/16/2023
3D-aware Conditional Image Synthesis
We propose pix2pix3D, a 3D-aware conditional generative model for contro...
research
∙
01/16/2023
Multimodality Helps Unimodality: Cross-Modal Few-Shot Learning with Multimodal Models
The ability to quickly learn a new task with minimal instruction - known...
research
∙
01/10/2023
Pix2Map: Cross-modal Retrieval for Inferring Street Maps from Images
Self-driving vehicles rely on urban street maps for autonomous navigatio...
research
∙
01/06/2023
TarViS: A Unified Approach for Target-based Video Segmentation
The general domain of video segmentation is currently fragmented into di...
research
∙
01/02/2023
Argoverse 2: Next Generation Datasets for Self-Driving Perception and Forecasting
We introduce Argoverse 2 (AV2) - a collection of three datasets for perc...
research
∙
11/25/2022
Far3Det: Towards Far-Field 3D Detection
We focus on the task of far-field 3D detection (Far3Det) of objects beyo...
research
∙
11/16/2022
Towards Long-Tailed 3D Detection
Contemporary autonomous vehicle (AV) benchmarks have advanced techniques...
research
∙
10/19/2022
Learning to Discover and Detect Objects
We tackle the problem of novel class discovery, detection, and localizat...
research
∙
10/10/2022
Learning with an Evolving Class Ontology
Lifelong learners must recognize concept vocabularies that evolve over t...
research
∙
10/04/2022
Dfferentiable Raycasting for Self-supervised Occupancy Forecasting
Motion planning for safe autonomous driving requires learning how the en...
research
∙
09/25/2022
BURST: A Benchmark for Unifying Object Recognition, Segmentation and Tracking in Video
Multiple existing benchmarks involve tracking and segmenting objects in ...
research
∙
08/11/2022
RelPose: Predicting Probabilistic Relative Rotation for Single Objects in the Wild
We describe a data-driven method for inferring the camera viewpoints giv...
research
∙
06/01/2022
Differentiable Soft-Masked Attention
Transformers have become prevalent in computer vision due to their perfo...
research
∙
05/22/2022
Robust Modeling and Controls for Racing on the Edge
Race cars are routinely driven to the edge of their handling limits in d...
research
∙
03/30/2022
Forecasting from LiDAR via Future Object Detection
Object detection and forecasting are fundamental components of embodied ...
research
∙
03/27/2022
Long-Tailed Recognition via Weight Balancing
In the real open world, data tends to follow long-tailed class distribut...
research
∙
01/17/2022
The CLEAR Benchmark: Continual LEArning on Real-World Imagery
Continual learning (CL) is widely regarded as crucial challenge for life...
research
∙
12/23/2021
BANMo: Building Animatable 3D Neural Models from Many Casual Videos
Prior work for articulated 3D shape reconstruction often relies on speci...
research
∙
12/20/2021
Mega-NeRF: Scalable Construction of Large-Scale NeRFs for Virtual Fly-Throughs
We use neural radiance fields (NeRFs) to build interactive 3D environmen...
research
∙
12/16/2021
HODOR: High-level Object Descriptors for Object Re-segmentation in Video Learned from Static Images
Existing state-of-the-art methods for Video Object Segmentation (VOS) le...
research
∙
10/14/2021
NeRS: Neural Reflectance Surfaces for Sparse-view 3D Reconstruction in the Wild
Recent history has seen a tremendous growth of work exploring implicit r...
research
∙
09/13/2021
Low-Shot Validation: Active Importance Sampling for Estimating Classifier Performance on Rare Categories
For machine learning models trained with limited labeled training data, ...
research
∙
08/27/2021
FOVEA: Foveated Image Magnification for Autonomous Navigation
Efficient processing of high-resolution video streams is safety-critical...
research
∙
07/06/2021
Depth-supervised NeRF: Fewer Views and Faster Training for Free
One common failure mode of Neural Radiance Field (NeRF) models is fittin...
research
∙
05/06/2021
LASR: Learning Articulated Shape Reconstruction from a Monocular Video
Remarkable progress has been made in 3D reconstruction of rigid structur...
research
∙
04/07/2021
Streaming Self-Training via Domain-Agnostic Unlabeled Images
We present streaming self-training (SST) that aims to democratize the pr...
research
∙
04/07/2021
OpenGAN: Open-Set Recognition via Open Data Generation
Real-world machine learning systems need to analyze novel testing data t...
research
∙
04/07/2021
Multimodal Object Detection via Bayesian Fusion
Object detection with multimodal inputs can improve many safety-critical...
research
∙
03/31/2021
Video Exploration via Video-Specific Autoencoders
We present simple video-specific autoencoders that enables human-control...
research
∙
02/01/2021
Evaluating Large-Vocabulary Object Detectors: The Devil is in the Details
By design, average precision (AP) for object detection aims to treat all...
research
∙
01/11/2021
Learning to Segment Rigid Motions from Two Frames
Appearance-based detectors achieve remarkable performance on common scen...
research
∙
12/15/2020
Detecting Invisible People
Monocular object detection and tracking have improved drastically in rec...
research
∙
08/28/2020
Background Splitting: Finding Rare Classes in a Sea of Background
We focus on the real-world problem of training accurate deep models for ...
research
∙
08/24/2020