Search Results for author:
Found 28 papers, 18 papers with code
Mesh2NeRF: Direct Mesh Supervision for Neural Radiance Field Representation and Generation
In Mesh2NeRF, we propose an analytic solution to directly obtain ground-truth radiance fields from 3D meshes, characterizing the density field with an occupancy function featuring a defined surface thickness, and determining view-dependent color through a reflection function considering both the mesh and environment lighting.
GIM: Learning Generalizable Image Matcher From Internet Videos
Given an architecture, GIM first trains it on standard domain-specific datasets and then combines it with complementary matching methods to create dense labels on nearby frames of novel videos.
EVP: Enhanced Visual Perception using Inverse Multi-Attentive Feature Refinement and Regularized Image-Text Alignment
Second, we propose a novel image-text alignment module for improved feature extraction of the Stable Diffusion backbone.
Ranked #1 on
Referring Expression Segmentation
on RefCOCO testB
Monocular Depth Estimation
Referring Expression Segmentation
Label Delay in Continual Learning
We introduce a new continual learning framework with explicit modeling of the label delay between data and label streams over time steps.
E2PNet: Event to Point Cloud Registration with Spatio-Temporal Representation Learning
While registration of 2D RGB images to 3D point clouds is a long-standing problem in computer vision, no prior work studies 2D-3D registration for event cameras.
MiDaS v3.1 -- A Model Zoo for Robust Monocular Relative Depth Estimation
We release MiDaS v3. 1 for monocular depth estimation, offering a variety of new models based on different encoder backbones.
Revisiting Test Time Adaptation under Online Evaluation
To address this issue, we propose a more realistic evaluation protocol for TTA methods, where data is received in an online fashion from a constant-speed data stream, thereby accounting for the method's adaptation speed.
Monocular Visual-Inertial Depth Estimation
We evaluate on the TartanAir and VOID datasets, observing up to 30% reduction in inverse RMSE with dense scale alignment relative to performing just global alignment alone.
ZoeDepth: Zero-shot Transfer by Combining Relative and Metric Depth
Finally, ZoeD-M12-NK is the first model that can jointly train on multiple datasets (NYU Depth v2 and KITTI) without a significant drop in performance and achieve unprecedented zero-shot generalization performance to eight unseen datasets from both indoor and outdoor domains.
Ranked #12 on
Monocular Depth Estimation
on NYU-Depth V2
(using extra training data)
Zero-Shot Transfer of Haptics-Based Object Insertion Policies
In this paper we train a contact-exploiting manipulation policy in simulation for the contact-rich household task of loading plates into a slotted holder, which transfers without any fine-tuning to the real robot.
SimCS: Simulation for Domain Incremental Online Continual Segmentation
This work explores the problem of Online Domain-Incremental Continual Segmentation (ODICS), where the model is continually trained over batches of densely labeled images from different domains, with limited computation and no information about the task boundaries.
Training Efficient Controllers via Analytic Policy Gradient
Conversely, learning-based offline optimization approaches, such as Reinforcement Learning (RL), allow fast and efficient execution on the robot but hardly match the accuracy of MPC in trajectory tracking tasks.
Learning High-Speed Flight in the Wild
Indeed, the subtasks are executed sequentially, leading to increased processing latency and a compounding of errors through the pipeline.
Jointly Learning Identification and Control for Few-Shot Policy Adaptation
We evaluate our approach on several complex systems and tasks, and experimentally analyze the advantages over model-free and model-based methods in terms of performance and sample efficiency.
Training Graph Neural Networks with 1000 Layers
Deep graph neural networks (GNNs) have achieved excellent results on various tasks on increasingly large graph datasets with millions of nodes and edges.
Ranked #1 on
Node Property Prediction
on ogbn-proteins
OpenBot: Turning Smartphones into Robots
We develop a software stack that allows smartphones to use this body for mobile operation and demonstrate that the system is sufficiently powerful to support advanced robotics workloads such as person following and real-time autonomous navigation in unstructured environments.
Deep Drone Acrobatics
In this paper, we propose to learn a sensorimotor policy that enables an autonomous quadrotor to fly extreme acrobatic maneuvers with only onboard sensing and computation.
Robotics
SGAS: Sequential Greedy Architecture Search
Architecture design has become a crucial component of successful deep learning.
Ranked #4 on
Node Classification
on PPI
DeepGCNs: Making GCNs Go as Deep as CNNs
This work transfers concepts such as residual/dense connections and dilated convolutions from CNNs to GCNs in order to successfully train very deep GCNs.
Ranked #5 on
3D Semantic Segmentation
on PartNet
Learning a Controller Fusion Network by Online Trajectory Filtering for Vision-based UAV Racing
A common approach is to learn an end-to-end policy that directly predicts controls from raw images by imitating an expert.
DeepGCNs: Can GCNs Go as Deep as CNNs?
Finally, we use these new concepts to build a very deep 56-layer GCN, and show how it significantly boosts performance (+3. 7% mIoU over state-of-the-art) in the task of point cloud semantic segmentation.
SADA: Semantic Adversarial Diagnostic Attacks for Autonomous Applications
In contrast, we present a general framework for adversarial attacks on trained agents, which covers semantic perturbations to the environment of the agent performing the task as well as pixel-level attacks.
Driving Policy Transfer via Modularity and Abstraction
Simulation can help end-to-end driving systems by providing a cheap, safe, and diverse training environment.
TrackingNet: A Large-Scale Dataset and Benchmark for Object Tracking in the Wild
In this work, we present TrackingNet, the first large-scale dataset and benchmark for object tracking in the wild.
OIL: Observational Imitation Learning
Recent work has explored the problem of autonomous navigation by imitating a teacher and learning an end-to-end policy, which directly predicts controls from raw images.
End-to-end Driving via Conditional Imitation Learning
However, driving policies trained via imitation learning cannot be controlled at test time.
Teaching UAVs to Race: End-to-End Regression of Agile Controls in Simulation
Automating the navigation of unmanned aerial vehicles (UAVs) in diverse scenarios has gained much attention in recent years.
Sim4CV: A Photo-Realistic Simulator for Computer Vision Applications
We present a photo-realistic training and evaluation simulator (Sim4CV) with extensive applications across various fields of computer vision.
