8 citations · 18 across the 26 of their papers we have counts for
28 papers
MimicAgent: Quadruped Skills via Prompt-to-Trajectory Generation
Lucky Kant Nayak, Narayanan Palghat Parameswaran, Neehar Peri +1
We present MimicAgent, a prompt-to-trajectory generation framework for learning dynamic quadruped skills. Although reward shaping is extensively used when training quadruped polici…
OV3D-Bench: A Diagnostic Benchmark for Open-Vocabulary Monocular 3D Detection
Mariia Gladkova, Neehar Peri, Ishan Khatri +2
Open-vocabulary monocular 3D detectors report strong in-domain performance, but each evaluates under a different protocol, several rely on per-image category oracles unavailable at…
Bridging Handheld and Teleoperated Supervision for Contact-Rich Manipulation via State-Gated Experts
Vidullan Surendran, Neehar Peri, David Watkins
Handheld data collection systems, such as the Universal Manipulation Interface (UMI), enable scalable data collection across diverse environments but only capture observed actions…
DetPO: In-Context Learning with Multi-Modal LLMs for Few-Shot Object Detection
Gautam Rajendrakumar Gare, Neehar Peri, Matvei Popov +3
Multi-Modal LLMs (MLLMs) demonstrate strong visual grounding capabilities on popular object detection benchmarks like OdinW-13 and RefCOCO. However, state-of-the-art models still s…
UniFlow: Zero-Shot LiDAR Scene Flow for Autonomous Vehicles
Siyi Li, Qingwen Zhang, Ishan Khatri +4
LiDAR scene flow is the task of estimating per-point 3D motion between consecutive point clouds. Recent methods achieve centimeter-level accuracy on popular autonomous vehicle (AV)…
RF-DETR: Neural Architecture Search for Real-Time Detection Transformers
Isaac Robinson, Peter Robicheaux, Matvei Popov +2
Open-vocabulary detectors achieve impressive performance on COCO, but often fail to generalize to real-world datasets with out-of-distribution classes not typically found in their…
MonoFusion: Sparse-View 4D Reconstruction via Monocular Fusion
Zihan Wang, Jeff Tan, Tarasha Khurana +2
We address the problem of dynamic scene reconstruction from sparse-view videos. Prior work often requires dense multi-view captures with hundreds of calibrated cameras (e.g. Panopt…
RefAV: Towards Planning-Centric Scenario Mining
Cainan Davidson, Deva Ramanan, Neehar Peri
Autonomous Vehicles (AVs) collect and pseudo-label terabytes of multi-modal data localized to HD maps during normal fleet testing. However, identifying interesting and safety-criti…
Roboflow100-VL: A Multi-Domain Object Detection Benchmark for Vision-Language Models
Peter Robicheaux, Matvei Popov, Anish Madan +4
Vision-language models (VLMs) trained on internet-scale data achieve remarkable zero-shot detection performance on common objects like car, truck, and pedestrian. However, state-of…
Towards Learning to Complete Anything in Lidar
Ayca Takmaz, Cristiano Saltori, Neehar Peri +4
We propose CAL (Complete Anything in Lidar) for Lidar-based shape-completion in-the-wild. This is closely related to Lidar-based semantic/panoptic scene completion. However, contem…
QuickDraw: Fast Visualization, Analysis and Active Learning for Medical Image Segmentation
Daniel Syomichev, Padmini Gopinath, Guang-Lin Wei +6
Analyzing CT scans, MRIs and X-rays is pivotal in diagnosing and treating diseases. However, detecting and identifying abnormalities from such medical images is a time-intensive pr…
Neural Eulerian Scene Flow Fields
Kyle Vedder, Neehar Peri, Ishan Khatri +7
We reframe scene flow as the task of estimating a continuous space-time ODE that describes motion for an entire observation sequence, represented with a neural prior. Our method, E…
Planning with Adaptive World Models for Autonomous Driving
Arun Balajee Vasudevan, Neehar Peri, Jeff Schneider +1
Motion planning is crucial for safe navigation in complex urban environments. Historically, motion planners (MPs) have been evaluated with procedurally-generated simulators like CA…
Shelf-Supervised Cross-Modal Pre-Training for 3D Object Detection
Mehar Khurana, Neehar Peri, James Hays +1
State-of-the-art 3D object detectors are often trained on massive labeled datasets. However, annotating 3D bounding boxes remains prohibitively expensive and time-consuming, partic…
Better Call SAL: Towards Learning to Segment Anything in Lidar
Aljoša Ošep, Tim Meinhardt, Francesco Ferroni +3
We propose the SAL (Segment Anything in Lidar) method consisting of a text-promptable zero-shot model for segmenting and classifying any object in Lidar, and a pseudo-labeling engi…
I Can't Believe It's Not Scene Flow!
Ishan Khatri, Kyle Vedder, Neehar Peri +2
Current scene flow methods broadly fail to describe motion on small objects, and current scene flow evaluation protocols hide this failure by averaging over many points, with most…
Revisiting Few-Shot Object Detection with Vision-Language Models
Anish Madan, Neehar Peri, Shu Kong +1
The era of vision-language models (VLMs) trained on web-scale datasets challenges conventional formulations of "open-world" perception. In this work, we revisit the task of few-sho…
Long-Tailed 3D Detection via Multi-Modal Fusion
Yechi Ma, Neehar Peri, Achal Dave +3
Contemporary autonomous vehicle (AV) benchmarks have significantly advanced multimodal (LiDAR+RGB) 3D detection. However, despite the naturally long-tailed distribution of object c…
An Empirical Analysis of Range for 3D Object Detection
Neehar Peri, Mengtian Li, Benjamin Wilson +3
LiDAR-based 3D detection plays a vital role in autonomous navigation. Surprisingly, although autonomous vehicles (AVs) must detect both near-field objects (for collision avoidance)…
ZeroFlow: Scalable Scene Flow via Distillation
Kyle Vedder, Neehar Peri, Nathaniel Chodosh +6
Scene flow estimation is the task of describing the 3D motion field between temporally successive point clouds. State-of-the-art methods use strong priors and test-time optimizatio…
ReBound: An Open-Source 3D Bounding Box Annotation Tool for Active Learning
Wesley Chen, Andrew Edgley, Raunak Hota +5
In recent years, supervised learning has become the dominant paradigm for training deep-learning based methods for 3D object detection. Lately, the academic community has studied 3…
A Brief Survey on Person Recognition at a Distance
Chrisopher B. Nalty, Neehar Peri, Joshua Gleason +4
Person recognition at a distance entails recognizing the identity of an individual appearing in images or videos collected by long-range imaging systems such as drones or surveilla…
Towards Long-Tailed 3D Detection
Neehar Peri, Achal Dave, Deva Ramanan +1
Contemporary autonomous vehicle (AV) benchmarks have advanced techniques for training 3D detectors, particularly on large-scale lidar data. Surprisingly, although semantic class la…
Forecasting from LiDAR via Future Object Detection
Neehar Peri, Jonathon Luiten, Mengtian Li +3
Object detection and forecasting are fundamental components of embodied perception. These two problems, however, are largely studied in isolation by the community. In this paper, w…