KS
Kalyan Sunkavalli
cs.CVcs.GRcs.LGcs.AIstat.MLAlgorithmscs.CLcs.ROeess.IVInterpersonal Relations
On Valency
published · living versionsW_7vbj8eng·v1 · currentpublished
AgiWorld: An Agentic Video World Model for Building Persistent Worlds
with Shaoheng Fang, Yiqun Mei, Hanwen Jiang, Xin Sun +5
1 version
Preprints & journals
71 papers in the corpus · 2007–2026Wonder: Video World Model Done Better2607.26037v1 · Jiacong Xu, Hanwen Jiang, Zhixin Shu et al.2026 · 0 citationsarXiv
SPEAR: A Simulator for Photorealistic Embodied AI Research2607.06701v1 · Mike Roberts, Renhan Wang, Rushikesh Zawar et al.2026 · 0 citationsarXiv
LooseControlVideo: Directorial Video Control using Spatial Blocking2606.19495v1 · Shariq Farooq Bhat, Niloy J. Mitra, Kalyan Sunkavalli2026 · 0 citationsarXiv
OmniRoam: World Wandering via Long-Horizon Panoramic Video Generation2603.30045v1 · Yuheng Liu, Xin Lin, Xinke Li et al.2026 · 1 citationarXiv
tttLRM: Test-Time Training for Long Context and Autoregressive 3D Reconstruction2602.20160v2 · Chen Wang, Hao Tan, Wang Yifan et al.2026 · 0 citationsarXiv
E-RayZer: Self-supervised 3D Reconstruction as Spatial Visual Pre-training2512.10950v2 · Qitao Zhao, Hao Tan, Qianqian Wang et al.2025 · 1 citationarXiv
RELIC: Interactive Video World Model with Long-Horizon Memory2512.04040v1 · Yicong Hong, Yiqun Mei, Chongjian Ge et al.2025 · 0 citationsarXiv
4D-LRM: Large Space-Time Reconstruction Model From and To Any View at Any Time2506.18890v1 · Ziqiao Ma, Xuweiyi Chen, Shoubin Yu et al.2025 · 5 citationsarXiv
Test-Time Training Done Right2505.23884v1 · Tianyuan Zhang, Sai Bi, Yicong Hong et al.2025 · 0 citationsarXiv
RayZer: A Self-supervised Large View Synthesis Model2505.00702v1 · Hanwen Jiang, Hao Tan, Peng Wang et al.2025 · 14 citationsarXiv
Neural Directional Encoding for Efficient and Accurate View-Dependent Appearance Modeling2405.14847v1 · Liwen Wu, Sai Bi, Zexiang Xu et al.2024 · 14 citationsarXiv
GS-LRM: Large Reconstruction Model for 3D Gaussian Splatting2404.19702v1 · Kai Zhang, Sai Bi, Hao Tan et al.2024 · 117 citationsarXiv
MeshLRM: Large Reconstruction Model for High-Quality Meshes2404.12385v2 · Xinyue Wei, Kai Zhang, Sai Bi et al.2024 · 0 citationsarXiv
DATENeRF: Depth-Aware Text-based Editing of NeRFs2404.04526v2 · Sara Rojas, Julien Philip, Kai Zhang et al.2024 · 7 citationsECCV 2024
LightIt: Illumination Modeling and Control for Diffusion Models2403.10615v2 · Peter Kocsis, Julien Philip, Kalyan Sunkavalli et al.2024 · 29 citationsarXiv
PF-LRM: Pose-Free Large Reconstruction Model for Joint Pose and Shape Prediction2311.12024v2 · Peng Wang, Hao Tan, Sai Bi et al.2023 · 11 citationsarXiv
DMV3D: Denoising Multi-View Diffusion using 3D Large Reconstruction Model2311.09217v1 · Yinghao Xu, Hao Tan, Fujun Luan et al.2023 · 25 citationsarXiv
Instant3D: Fast Text-to-3D with Sparse-View Generation and Large Reconstruction Model2311.06214v2 · Jiahao Li, Hao Tan, Kai Zhang et al.2023 · 32 citationsarXiv
LRM: Large Reconstruction Model for Single Image to 3D2311.04400v2 · Yicong Hong, Kai Zhang, Jiuxiang Gu et al.2023 · 31 citationsarXiv
Controllable Dynamic Appearance for Neural 3D Portraits2309.11009v2 · ShahRukh Athar, Zhixin Shu, Zexiang Xu et al.2023 · 0 citationsarXiv
A Perceptual Measure for Deep Single Image Camera and Lens Calibration.37195850 · Hold-Geoffroy, Yannick, Piche-Meunier, Dominique, Sunkavalli, Kalyan et al.2023 · 13 citationsIEEE transactions on pattern analysis and machine intelligence. 2023;45(9):10603-10614
NeuManifold: Neural Watertight Manifold Reconstruction with Efficient and High-Quality Rendering Support2305.17134v3 · Xinyue Wei, Fanbo Xiang, Sai Bi et al.2023 · 5 citationsarXiv
PhotoMat: A Material Generator Learned from Single Flash Photos2305.12296v2 · Xilong Zhou, Milos Hasan, Valentin Deschaintre et al.2023 · 32 citationsSiggraph 2023
PaletteNeRF: Palette-based Appearance Editing of Neural Radiance Fields2212.10699v2 · Zhengfei Kuang, Fujun Luan, Sai Bi et al.2022 · 56 citationsarXiv
Snapshot polarimetric diffuse-specular separation.36242441 · Dave, Akshat, Hold-Geoffroy, Yannick, Hašan, Miloš et al.2022 · 9 citationsOptics express. 2022;30(19):34239-34255
A Deep Perceptual Measure for Lens and Camera Calibration2208.12300v2 · Yannick Hold-Geoffroy, Dominique Pich'e-Meunier, Kalyan Sunkavalli et al.2022 · 2 citationsarXiv
MatFormer: A Generative Model for Procedural Materials2207.01044v2 · Paul Guerrero, Milos Hasan, Kalyan Sunkavalli et al.2022 · 45 citationsACM Transactions on Graphics, Volume 41, Issue 4 (Proceedings of Siggraph 2022)
PhotoScene: Photorealistic Material and Lighting Transfer for Indoor Scenes2207.00757v1 · Yu-Ying Yeh, Zhengqin Li, Yannick Hold-Geoffroy et al.2022 · 32 citationsarXiv
RigNeRF: Fully Controllable Neural 3D Portraits2206.06481v1 · ShahRukh Athar, Zexiang Xu, Kalyan Sunkavalli et al.2022 · 130 citationsarXiv
TileGen: Tileable, Controllable Material Generation and Capture2206.05649v2 · Xilong Zhou, Milos Hasan, Valentin Deschaintre et al.2022 · 47 citationsarXiv
Differentiable Rendering of Neural SDFs through Reparameterization2206.05344v1 · Sai Praveen Bangaru, Michael Gharbi, Tzu-Mao Li et al.2022 · 41 citationsarXiv
Physically-Based Editing of Indoor Scene Lighting from a Single Image2205.09343v2 · Zhengqin Li, Jia Shi, Sai Bi et al.2022 · 46 citationsarXiv
NeRFusion: Fusing Radiance Fields for Large-Scale Scene Reconstruction2203.11283v1 · Xiaoshuai Zhang, Sai Bi, Kalyan Sunkavalli et al.2022 · 102 citationsarXiv
Interactive Portrait Harmonization2203.08216v1 · Jeya Maria Jose Valanarasu, He Zhang, Jianming Zhang et al.2022 · 11 citationsarXiv
Point-NeRF: Point-based Neural Radiance Fields2201.08845v7 · Qiangeng Xu, Zexiang Xu, Julien Philip et al.2022 · 592 citationsIn Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (pp. 5438-5448) (2022)
SSH: A Self-Supervised Framework for Image Harmonization2108.06805v2 · Yifan Jiang, He Zhang, Jianming Zhang et al.2021 · 79 citationsarXiv
Self-Supervised Multi-View Person Association and its Applications.32086193 · Vo, Minh, Yumer, Ersin, Sunkavalli, Kalyan et al.2021 · 25 citationsIEEE transactions on pattern analysis and machine intelligence. 2021;43(8):2794-2808
NeuTex: Neural Texture Mapping for Volumetric Neural Rendering2103.00762v1 · Fanbo Xiang, Zexiang Xu, Milos Hasan et al.2021 · 103 citationsarXiv
Deep Denoising of Flash and No-Flash Pairs for Photography in Low-Light Environments2012.05116v2 · Zhihao Xia, Michael Gharbi, Federico Perazzi et al.2020 · 21 citationsarXiv
MaterialGAN: Reflectance Capture using a Generative SVBRDF Model2010.00114v1 · Yu Guo, Cameron Smith, Milos Hasan et al.2020 · 121 citationsarXiv
Neural Reflectance Fields for Appearance Acquisition2008.03824v2 · Sai Bi, Zexiang Xu, Pratul Srinivasan et al.2020 · 124 citationsarXiv
Deep Multi Depth Panoramas for View Synthesis2008.01815v1 · Kai-En Lin, Zexiang Xu, Ben Mildenhall et al.2020 · 31 citationsarXiv
OpenRooms: An End-to-End Open Framework for Photorealistic Indoor Scene Datasets2007.12868v3 · Zhengqin Li, Ting-Wei Yu, Shen Sang et al.2020 · 11 citationsarXiv
Deep Reflectance Volumes: Relightable Reconstructions from Multi-View Photometric Images2007.09892v1 · Sai Bi, Zexiang Xu, Kalyan Sunkavalli et al.2020 · 106 citationsarXiv
Single View Metrology in the Wild2007.09529v3 · Rui Zhu, Xingyi Yang, Yannick Hold-Geoffroy et al.2020 · 38 citationsarXiv
State of the Art on Neural Rendering2004.03805v1 · Ayush Tewari, Ohad Fried, Justus Thies et al.2020 · 453 citationsarXiv
Deep 3D Capture: Geometry and Reflectance from Sparse Multi-View Images2003.12642v2 · Sai Bi, Zexiang Xu, Kalyan Sunkavalli et al.2020 · 90 citationsarXiv
Deep CG2Real: Synthetic-to-Real Translation via Image Disentanglement2003.12649v1 · Sai Bi, Kalyan Sunkavalli, Federico Perazzi et al.2020 · 31 citationsarXiv
Automatic Scene Inference for 3D Object Compositing1912.12297v1 · Kevin Karsch, Kalyan Sunkavalli, Sunil Hadap et al.2019 · 181 citationsarXiv
Basis Prediction Networks for Effective Burst Denoising with Large Kernels1912.04421v2 · Zhihao Xia, Federico Perazzi, Michael Gharbi et al.2019 · 66 citationsarXiv
Career total: 140 works. 71 are in this corpus.Showing the 50 most recent.
Profile built from the corpus for this byline.
Author records are still filling in while the Hub is in alpha. If this is your page, you'll be able to claim it soon. Spot a mistake? Tell us.