7 citations · 11 across the 33 of their papers we have counts for
33 papers · 1 filter
SplatLab: Autonomous Scientific Discovery for 3DGS Research
Seemandhar Jain, Manmohan Chandraker
Reproducing a published 3DGS paper takes weeks of expert engineering before any extension can be proposed. Prior autonomous-research systems read papers, draft hypotheses, and writ…
HorizonComposer: Spatiotemporally Consistent Driving Video Editing with Enriched Traffic Semantics
Mauricio Soroco, Yuqiu Liu, Zaid Tasneem +5
Instruction-guided video generative models offer a scalable solution for stress-testing autonomous driving systems by simulating diverse environmental conditions. However, driving…
SPLATIFY: Reproduce, Discover, Innovate! From Papers and Ideas to Trainable 3DGS Code
Seemandhar Jain, Keshav Gupta, Manmohan Chandraker
The rapid growth of 3D Gaussian Splatting (3DGS) research demands significant effort to reimplement papers before building on them. We introduce SPLATIFY, a multi-agent framework t…
Learning How the World Evolves: Extrapolative Video World Models via Latent Dynamics Reasoning
Haodong Li, Shaoteng Liu, Tianyu Wang +7
The world evolves following its dynamics, i.e., its laws of motion. However, leading video diffusion models largely fit the pixels without modeling how the pixels transit over time…
Reflecting Process Expertise in Procedural Material Generation
Kunal Gupta, Gaurav Joshi, Yen-Ru Chen +3
Procedural material creation underpins applications in digital content creation, visual effects, and 3D asset design. Achieving high-quality results requires more than reproducing…
Dash2Sim: Closed-Loop Driving Simulation from in-the-wild Dashcam Videos
Anurag Ghosh, Francesco Pittaluga, Khiem Vuong +4
Self-driving simulations typically rely on data collected in a small number of cities or on hand-authored synthetic scenarios. Dashcam videos cover a far broader range of locations…
What to Test Next: Interpretable Coverage Gap Discovery in Driving VLMs
Abhishek Aich, Sparsh Garg, Vijay Kumar BG +2
Driving vision-language models (VLMs) must accurately understand scenes across diverse conditions defined by Operational Design Domains (ODDs), yet verification remains sparse: man…
-Scene: Physically Grounded Image-to-3D Scene Reconstruction
Haodong Li, Lulu Shao, Haolin Lu +4
Recent image-to-3D scene methods recover high-fidelity 3D objects with plausible arrangements, but often leave floatings and interpenetrations that limit physical validity and down…
PhyCo: Learning Controllable Physical Priors for Generative Motion
Sriram Narayanan, Ziyu Jiang, Srinivasa Narasimhan +1
Modern video diffusion models excel at appearance synthesis but still struggle with physical consistency: objects drift, collisions lack realistic rebound, and material responses s…
HorizonWeaver: Generalizable Multi-Level Semantic Editing for Driving Scenes
Mauricio Soroco, Francesco Pittaluga, Zaid Tasneem +5
Ensuring safety in autonomous driving requires scalable generation of realistic, controllable driving scenes beyond what real-world testing provides. Yet existing instruction guide…
HorizonForge: Driving Scene Editing with Any Trajectories and Any Vehicles
Yifan Wang, Francesco Pittaluga, Zaid Tasneem +3
Controllable driving scene generation is critical for realistic and scalable autonomous driving simulation, yet existing approaches struggle to jointly achieve photorealism and pre…
NERFIFY: A Multi-Agent Framework for Turning NeRF Papers into Code
Seemandhar Jain, Keshav Gupta, Kunal Gupta +1
The proliferation of neural radiance field (NeRF) research requires significant efforts to reimplement papers before building upon them. We introduce NERFIFY, a multi-agent framewo…
Rolling Sink: Bridging Limited-Horizon Training and Open-Ended Testing in Autoregressive Video Diffusion
Haodong Li, Shaoteng Liu, Zhe Lin +1
Autoregressive (AR) video diffusion models in the Self Forcing family generate a video chunk by chunk, each conditioned on the ones before it, so they can keep rolling out with no…
LangDriveCTRL: Natural Language Controllable Driving Scene Editing with Multi-modal Agents
Yun He, Francesco Pittaluga, Ziyu Jiang +3
LangDriveCTRL is a natural-language-controllable framework for editing real-world driving videos to synthesize diverse traffic scenarios. It represents each video as an explicit 3D…
AutoScape: Geometry-Consistent Long-Horizon Scene Generation
Jiacheng Chen, Ziyu Jiang, Mingfu Liang +5
This paper proposes AutoScape, a long-horizon driving scene generation framework. At its core is a novel RGB-D diffusion model that iteratively generates sparse, geometrically cons…
iFinder: Structured Zero-Shot Vision-Based LLM Grounding for Dash-Cam Video Reasoning
Manyi Yao, Bingbing Zhuang, Sparsh Garg +4
Grounding large language models (LLMs) in domain-specific tasks like post-hoc dash-cam driving video analysis is challenging due to their general-purpose training and lack of struc…
ST-VLM: Kinematic Instruction Tuning for Spatio-Temporal Reasoning in Vision-Language Models
Dohwan Ko, Sihyeon Kim, Yumin Suh +4
Spatio-temporal reasoning is essential in understanding real-world environments in various fields, eg, autonomous driving and sports analytics. Recent advances have improved the sp…
DWIM: Towards Tool-aware Visual Reasoning via Discrepancy-aware Workflow Generation & Instruct-Masking Tuning
Fucai Ke, Vijay Kumar B G, Xingjian Leng +6
Visual reasoning (VR), which is crucial in many fields for enabling human-like visual understanding, remains highly challenging. Recently, compositional visual reasoning approaches…
Materialist: Physically Based Editing Using Single-Image Inverse Rendering
Lezhong Wang, Duc Minh Tran, Ruiqi Cui +5
Achieving physically consistent image editing remains a significant challenge in computer vision. Existing image editing methods typically rely on neural networks, which struggle t…
Drive-1-to-3: Enriching Diffusion Priors for Novel View Synthesis of Real Vehicles
Chuang Lin, Bingbing Zhuang, Shanlin Sun +3
The recent advent of large-scale 3D data, e.g. Objaverse, has led to impressive progress in training pose-conditioned diffusion models for novel view synthesis. However, due to the…
Robust Disaster Assessment from Aerial Imagery Using Text-to-Image Synthetic Data
Tarun Kalluri, Jihyeon Lee, Kihyuk Sohn +4
We present a simple and efficient method to leverage emerging text-to-image generative models in creating large-scale synthetic supervision for the task of damage assessment from a…
Instantaneous Perception of Moving Objects in 3D
Di Liu, Bingbing Zhuang, Dimitris N. Metaxas +1
The perception of 3D motion of surrounding traffic participants is crucial for driving safety. While existing works primarily focus on general large motions, we contend that the in…
LidaRF: Delving into Lidar for Neural Radiance Field on Street Scenes
Shanlin Sun, Bingbing Zhuang, Ziyu Jiang +3
Photorealistic simulation plays a crucial role in applications such as autonomous driving, where advances in neural radiance fields (NeRFs) may allow better scalability through the…
Self-Training Large Language Models for Improved Visual Program Synthesis With Visual Reinforcement
Zaid Khan, Vijay Kumar BG, Samuel Schulter +2
Visual program synthesis is a promising approach to exploit the reasoning abilities of large language models for compositional computer vision tasks. Previous work has used few-sho…