TK

Tarasha Khurana

cs.CVcs.AIcs.LGcs.ROeess.SP

On Valency

published · living versions

Hierarchical Diffusion for Camera-controlled Autoregressive Video Generation

with Kaihua Chen, Yiming Gong, Deva Ramanan

1 version

W_4gxv526vv1 · current

Preprints & journals

10 papers in the corpus · 2020–2025

MonoFusion: Sparse-View 4D Reconstruction via Monocular Fusion

Zihan Wang, Jeff Tan, Tarasha Khurana et al.

5 citations

2507.23782v22025arXiv

Reconstruct, Inpaint, Test-Time Finetune: Dynamic Novel-view Synthesis from Monocular Videos

Kaihua Chen, Tarasha Khurana, Deva Ramanan

4 citations

2507.12646v22025arXiv

Using Diffusion Priors for Video Amodal Segmentation

Kaihua Chen, Deva Ramanan, Tarasha Khurana

8 citations

2412.04623v12024arXiv

Predicting Long-horizon Futures by Conditioning on Geometry and Time

Tarasha Khurana, Deva Ramanan

0 citations

2404.11554v12024arXiv

TAO-Amodal: A Benchmark for Tracking Any Object Amodally

Cheng-Yen Hsieh, Kaihua Chen, Achal Dave et al.

3 citations

2312.12433v32023arXiv

Point Cloud Forecasting as a Proxy for 4D Occupancy Forecasting

Tarasha Khurana, Peiyun Hu, David Held et al.

40 citations

2302.13130v32023arXiv

Differentiable Raycasting for Self-supervised Occupancy Forecasting

Tarasha Khurana, Peiyun Hu, Achal Dave et al.

60 citations

2210.01917v22022arXiv

BURST: A Benchmark for Unifying Object Recognition, Segmentation and Tracking in Video

Ali Athar, Jonathon Luiten, Paul Voigtlaender et al.

56 citations

2209.12118v22022arXiv

Detecting Invisible People

Tarasha Khurana, Achal Dave, Deva Ramanan

43 citations

2012.08419v12020arXiv

TAO: A Large-Scale Benchmark for Tracking Any Object

Achal Dave, Tarasha Khurana, Pavel Tokmakov et al.

165 citations

2005.10356v12020arXiv

Career total: 22 works. 10 are in this corpus.

Profile built from the corpus for this byline.

Author records are still filling in while the Hub is in beta. If this is your page, you'll be able to claim it soon. Spot a mistake? Tell us.