Tarasha Khurana
@tarashakhurana
PhD student @ CMU RI
Excited to share recent work with @kaihuac5 and @RamananDeva where we learn to do novel view synthesis for dynamic scenes in a self-supervised manner, only from 2D videos! webpage: cog-nvs.github.io arxiv: arxiv.org/abs/2507.12646 code (soon): github.com/Kaihua-Chen/co…
Research arc: ⏪ 2 yrs ago, we introduced VRB: learning from hours of human videos to cut down teleop (Gibson🙏) ▶️ Today, we explore a wilder path: robots deployed with no teleop, no human demos, no affordances. Just raw video generation magic 🙏 Day 1 of faculty life done! 😉…
🚀 Introducing RIGVid: Robots Imitating Generated Videos! Robots can now perform complex tasks—pouring, wiping, mixing—just by imitating generated videos, purely zero-shot! No teleop. No OpenX/DROID/Ego4D. No videos of human demonstrations. Only AI generated video demos 🧵👇
Super cool new work on NVS for dynamic scenes! 🚀☺️
Excited to share recent work with @kaihuac5 and @RamananDeva where we learn to do novel view synthesis for dynamic scenes in a self-supervised manner, only from 2D videos! webpage: cog-nvs.github.io arxiv: arxiv.org/abs/2507.12646 code (soon): github.com/Kaihua-Chen/co…
Cool work! Diffusion models have been used for out and in painting 2d images already. Quite smart to use these priors for automatically completing unseen regions in dynamic scenes. I can see this being a quick boost for many robotics applications!
Excited to share recent work with @kaihuac5 and @RamananDeva where we learn to do novel view synthesis for dynamic scenes in a self-supervised manner, only from 2D videos! webpage: cog-nvs.github.io arxiv: arxiv.org/abs/2507.12646 code (soon): github.com/Kaihua-Chen/co…
always exciting to see clever use of pre-trained diffusion models for hard applications! cool work from friends @CMU_Robotics
Excited to share recent work with @kaihuac5 and @RamananDeva where we learn to do novel view synthesis for dynamic scenes in a self-supervised manner, only from 2D videos! webpage: cog-nvs.github.io arxiv: arxiv.org/abs/2507.12646 code (soon): github.com/Kaihua-Chen/co…
Checkout @tarashakhurana's work on using video diffusion models for dynamic novel view synthesis!
Excited to share recent work with @kaihuac5 and @RamananDeva where we learn to do novel view synthesis for dynamic scenes in a self-supervised manner, only from 2D videos! webpage: cog-nvs.github.io arxiv: arxiv.org/abs/2507.12646 code (soon): github.com/Kaihua-Chen/co…
"Reconstruct, Inpaint, Finetune: Dynamic Novel-view Synthesis from Monocular Videos" TL;DR : Video diffusion model for dynamic novel-view synthesis trained in a self-supervised manner using only 2D videos. Novel-view synthesis as a structured inpainting task: (2/3)
Reconstruct, Inpaint, Finetune: Dynamic Novel-view Synthesis from Monocular Videos TL;DR: CogNVS is a video diffusion model for dynamic novel-view synthesis, trained in a self-supervised manner using only 2D videos! - We first reconstruct input views with off-the-shelf SLAM…
Reconstruct, Inpaint, Finetune: Dynamic Novel-view Synthesis from Monocular Videos @kaihuac5, @tarashakhurana, @RamananDeva tl;dr: in title; fine-tune CogVideoX->train 2D video-inpainter arxiv.org/abs/2507.12646
AllTracker: Efficient Dense Point Tracking at High Resolution If you're using any point tracker in any project, this is likely a drop-in upgrade—improving speed, accuracy, and density, all at once.
This was a really fun and exciting workshop #CVPR2025! Huge thanks to all the speakers, organizers and reviewers @CVPR! We hope to be able to release the video recordings soon!
Join us for the 4D Vision Workshop @CVPR on June 11 starting at 9:20am! We'll have an incredible lineup of speakers discussing the frontier of 3D computer vision techniques for dynamic world modeling across spatial AI, robotics, astrophysics, and more. 4dvisionworkshop.github.io
Had a great time at @CVPR! So grateful for the Consortium where I could get lots of great career advice from @xiaolonw :) Hope this program continues in future iterations of CVPR. Huge congrats to @kaihuac5 who also presented his amazing work!


My amazing partner @tarashakhurana is presenting at Poster #174! #CVPR2025 Go check it out!
I'll be at @CVPR this week -- organizing the Workshop on 4D Vision, attending Doctoral Consortium and presenting one of our recent works (poster 174 in session 5)! I'm also actively looking for Research Scientist roles. Happy to chat! CV is here: cs.cmu.edu/~tkhurana/pdf/…
Join us for the 4D Vision Workshop @CVPR on June 11 starting at 9:20am! We'll have an incredible lineup of speakers discussing the frontier of 3D computer vision techniques for dynamic world modeling across spatial AI, robotics, astrophysics, and more. 4dvisionworkshop.github.io
Robots need touch for human-like hands to reach the goal of general manipulation. However, approaches today don’t use tactile sensing or use specific architectures per tactile task. Can 1 model improve many tactile tasks? 🌟Introducing Sparsh-skin: tinyurl.com/y935wz5c 1/6
🚨 The 2nd iteration of our @CVPR Foundational Few-Shot Object Detection Challenge is LIVE! Can your model think like an annotator? 🧠💥 Align Vision-Language Models (VLMs) with a few multi-modal examples & win 💰 cash prizes! 🔗 Challenge: eval.ai/web/challenges…
We released the inference and evaluation code for this work! Feel free to try it out on your videos :-) github.com/Kaihua-Chen/di…
Excited to present new work on using diffusion priors for video amodal segmentation and content completion! with @kaihuac5 (lead author) and @RamananDeva arXiv: arxiv.org/abs/2412.04623 project page: diffusion-vas.github.io
Submission deadline has been extended by a week to April 4. Submit your latest 4D work to the workshop @CVPR: 4D Gaussians, point tracking, dynamic SLAMs, egocentric, human motion, multi-modal world models, embodied AI... you name it! 4dvisionworkshop.github.io
Really excited to put together this @CVPR workshop on "4D Vision: Modeling the Dynamic World" -- one of the most fascinating areas in computer vision today! We've invited incredible researchers who are leading fantastic work at various related fields. 4dvisionworkshop.github.io