Recent and Selected Papers

• Tianhao Wu, Chuanxia Zheng, Tat-Jen Cham, Qianyi Wu, ClusteringSDF: Self-organized neural implicit surfaces for 3D decomposition, arXiv:2403.14619 [cs.CV], Mar 2024. [arxiv, project]
• Yuedong Chen, Haofei Xu, Chuanxia Zheng, Bohan Zhuang, Marc Pollefeys, Andreas Geiger, Tat-Jen Cham, Jianfei Cai, MVSplat: Efficient 3D Gaussian splatting from sparse multi-view images, arXiv:2403.14627 [cs.CV], Mar 2024. [arxiv, project]
• Minghui Hu, Jianbin Zheng, Chuanxia Zheng, Chaoyue Wang, Dacheng Tao, Tat-Jen Cham, One More Step: A versatile plug-and-play module for rectifying diffusion schedule flaws and enhancing low-frequency controls, CVPR, 2024. [arxiv, project, demo]
• Tianhao Wu, Chuanxia Zheng, Tat-Jen Cham, PanoDiffusion: 360-degree panorama outpainting via diffusion, ICLR, 2024. [arxiv, openreview, local, project]
• Minghui Hu, Jianbin Zheng, Daqing Liu, Chuanxia Zheng, Chaoyue Wang, Dacheng Tao, Tat-Jen Cham, Cocktail: Mixing multi-modality controls for text-conditional image generation, NeurIPS, 2023. [arxiv, openreview, neurips, local, project, youtube]
• Zhe Jun Tang, Tat-Jen Cham, Haiyu Zhao, ABLE-NeRF: attention-based rendering with learnable embeddings for neural radiance field, CVPR, 2023. [arxiv, cvf, github, local, poster]
• Minghui Hu, Chuanxia Zheng, Heliang Zheng, Tat-Jen Cham, Chaoyue Wang, Zuopeng Yang, Dacheng Tao, Ponnuthurai N. Suganthan, UniD3: Unified discrete diffusion for simultaneous vision-language generation, ICLR, 2023. [arxiv, openreview, local, project]
• Bo Hu, Tat-Jen Cham, Entry-flipped transformer for inference and prediction of participant behavior, ECCV, 2022. [arxiv, ecva, local, youtube]
• Yuedong Chen, Qianyi Wu, Chuanxia Zheng, Tat-Jen Cham, Jianfei Cai, Sem2NeRF: Converting single-view semantic masks to neural radiance fields, ECCV, 2022. [arxiv, ecva, local, project, youtube]
• Guoxian Song, Tat-Jen Cham, Jianfei Cai, Jianmin Zheng, Real-time shadow-aware portrait relighting in virtual backgrounds for realistic telepresence , IEEE ISMAR, 2022. [ieee, local, youtube]
• Zhe Jun Tang, Tat-Jen Cham, MPT-Net: Mask point transformer network for large scale point cloud semantic segmentation, IROS, 2022. [ieee, local]
• Yuedong Chen, Xu Yang, Tat-Jen Cham, Jianfei Cai, Towards unbiased visual emotion recognition via causal intervention, ACM Multimedia, 2022. [arxiv, acm, local]
• Chuanxia Zheng, Tat-Jen Cham, Jianfei Cai, Dinh Phung, Bridging global context interactions for high-fidelity image completion, CVPR, 2022. [arxiv, cvf, local, github, youtube]
• Minghui Hu, Yujie Wang, Tat-Jen Cham, Jianfei Yang, Ponnuthurai Suganthan, Global context with discrete diffusion in vector quantised modelling for image generation, CVPR, 2022. [arxiv, cvf, local]
• Chuanxia Zheng, Duy-Son Dao, Guoxian Song, Tat-Jen Cham, Jianfei Cai, Visiting the invisible: layer-by-layer completed scene decomposition, IJCV, 2021 [arxiv, springer, local, github, youtube].
• Yuedong Chen, Guoxian Song, Zhiwen Shao, Jianfei Cai, Tat-Jen Cham, Jianmin Zheng, GeoConv: geodesic guided convolution for facial action unit recognition, Pattern Recognition, 122:118355, 2022. [arxiv, elsevier, local]
• Zhiwen Shao, Jianfei Cai, Tat-Jen Cham, Xuequan Lu, Lizhuang Ma, Unconstrained facial action unit detection via latent feature domain, IEEE Trans. Affective Computing (TAC), 2021.[arxiv, ieee, local]
• Yujun Cai, Yiwei Wang, Yiheng Zhu, Tat-Jen Cham, Jianfei Cai, Junsong Yuan, Jun Liu, Chuanxia Zheng, Sijie Yan, Henghui Ding, Xiaohui Shen, Ding Liu, Nadia Magenat Thalmann, A unified 3D human motion synthesis model via conditional variational auto-encoder, ICCV, 2021 [cvf, local, github].
• Chuanxia Zheng, Tat-Jen Cham, Jianfei Cai, Pluralistic free-form image completion, IJCV, 2021. [springer, local]
• Guoxian Song, Linjie Luo, Jing Liu, Wan-Chun Ma, Chunpong Lai, Chuanxia Zheng, Tat-Jen Cham, AgileGAN: stylizing portraits by inversion-consistent transfer learning, SIGGRAPH, 2021. [acm, local, github, youtube]
• Guoxian Song, Tat-Jen Cham, Jianfei Cai, Jianmin Zheng, Half-body portrait relighting with overcomplete lighting representation, Computer Graphics Forum (CGF), 2021. [wiley, local, youtube]
• Chuanxia Zheng, Tat-Jen Cham, Jianfei Cai, The spatially-correlative loss for various image translation tasks, CVPR, 2021. [arxiv, cvf, local, github, youtube]
• Yujun Cai, Lin Huang, Yiwei Wang, Tat-Jen Cham, Jianfei Cai, Junsong Yuan, Jun Liu, Xu Yang, Yiheng Zhu, Xiaohui Shen, Ding Liu, Jing Liu, Nadia Magnenat Thalmann, Learning progressive joint propagation for human motion prediction, ECCV, 2020. [ecva, local]
• Guoxian Song, Jianmin Zheng, Jianfei Cai, Tat-Jen Cham, Recovering facial reflectance and geometry from multi-view images, Image and Vision Computing, 2020. [arxiv, elsevier, local]
• Xinxing Xia, Yunqing Guan, Andrei State, Praneeth Chakravarthula, Tat-Jen Cham, Henry Fuchs, Towards eyeglass-style holographic near-eye displays with statically expanded eyebox, ISMAR, 2020. [ieee, local]
• Yujun Cai, Liuhao Ge, Jun Liu, Jianfei Cai, Tat-Jen Cham, Junsong Yuan, Nadia Thalmann, Exploiting spatial-temporal relationships for 3D pose estimation via graph convolutional networks, ICCV, 2019. [cvf, local, github]
• Xinxing Xia, Yunqing Guan, Andrei State, Praneeth Chakravarthula, Kishore Rathinavel, Tat-Jen Cham, Henry Fuchs, Towards a switchable AR/VR near-eye display with accommodation-vergence and eyeglass prescription support, ISMAR and Special Issue of IEEE TVCG, 2019. [ieee, local]
• Chuanxia Zheng, Tat-Jen Cham, Jianfei Cai, Pluralistic image completion, CVPR, 2019. [arxiv, cvf, local, github, youtube]
• Teng Deng, Jianmin Zheng, Jianfei Cai, Tat-Jen Cham, Shading-based surface recovery using subdivision-based representation, CGF, 2019. [wiley, local]
• Lu Sheng, Jianfei Cai, Tat-Jen Cham, Vladimir Pavlovic, King Ngi Ngan, Visibility constrained generative model for depth-based 3D facial pose tracking, IEEE T-PAMI, 2018. [ieee, local]
• Guoxian Song, Jianfei Cai, Tat-Jen Cham, Jianmin Zheng, Juyong Zhang, Henry Fuchs, Real-time 3D face-eye performance capture of a person wearing VR headset, ACM Multimedia, 2018 [arxiv, acm, local, youtube]
• Chuanxia Zheng, Tat-Jen Cham, Jianfei Cai, T2Net: synthetic-to-realistic translation for solving single-image depth estimation tasks, ECCV, 2018. [arxiv, cvf, local, github]
• Chenqiu Zhao, Tat-Jen Cham, Xinyu Ren, Jianfei Cai, Haichen Zhu, Background subtraction based on deep pixel distribution learning, ICME, 2018. [ieee, local]
• Di Xu, Qi Duan, Jianmin Zheng, Juyong Zhang, Jianfei Cai, Tat-Jen Cham, Shading-based surface detail recovery under general unknown illumination, IEEE T-PAMI, 40(2): 423-436, 2018. [ieee, local]
• Anran Wang, Jianfei Cai, Jiwen Lu, Tat-Jen Cham, Structure-aware multimodal feature fusion for RGB-D scene classification and beyond. ACM TOMM, 14(2s): 39:1-39:22, 2018 . [acm ,local]
• Xinxing Xia, Yunqing Guan, Andrei State, Tat-Jen Cham, Henry Fuchs, Towards efficient 3D calibration for different types of multi-view autostereoscopic 3D displays. CGI, 2018. [acm, local]
• Teng Deng, Jianfei Cai, Tat-Jen Cham, Jianmin Zheng, Multiple consumer-grade depth camera registration using everyday objects. Image & Vision Computing, 62: 1-7, 2017. [scd, local]
• Lu Sheng, Jianfei Cai, Tat-Jen Cham, Vladimir Pavlovic, King Ngi Ngan, A generative model for depth-based robust 3D facial pose tracking. CVPR, 2017. [cvf, local]
• Fuwen Tan, Chi-Wing Fu, Teng Deng, Jianfei Cai, Tat-Jen Cham, FaceCollage: a rapidly deployable system for real-time head reconstruction for on-the-go 3D telepresence. ACM Multimedia, 2017. [acm, local]
• Hai X. Pham, Vladimir Pavlovic, Jianfei Cai, Tat-Jen Cham, Robust real-time performance-driven 3D face tracking, ICPR, 2016. [ieee, local]
• Anran Wang, Jianfei Cai, Jiwen Lu, Tat-Jen Cham, Modality and component aware feature fusion for RGB-D scene classification, CVPR, 2016. [cvf, local]
• Anran Wang, Jiwen Lu, Jianfei Cai, Gang Wang, Tat-Jen Cham, Unsupervised joint feature learning and encoding for RGB-D scene labeling, IEEE TIP, 24(11): 4459-4473, 2015. [ieee, local]
• Chongyu Chen, Jianfei Cai, Jianmin Zheng, Tat-Jen Cham, Guangming Shi, Kinect depth recovery using a color-guided, region-adaptive, and depth-selective framework. ACM TIST, 6(2): 12:1-12:19, 2015. [acm, local]
• Marcus Chen, Ivor W. Tsang, Mingkui Tan, Tat-Jen Cham, A unified feature selection framework for graph embedding on high dimensional data. IEEE TKDE, 27(6): 1465-1477, 2015. [ieee, local]
• Anran Wang, Jiwen Lu, Jianfei Cai, Tat-Jen Cham, Gang Wang, Large-margin multi-modal deep learning for RGB-D object recognition. IEEE TMM, 17(11): 1887-1898, 2015. [ieee, local]
• Anran Wang, Jianfei Cai, Jiwen Lu, Tat-Jen Cham, MMSS: Multi-modal sharable and specific feature learning for RGB-D object recognition. ICCV, 2015. [cvf, local]
• Di Xu, Qi Duan, Jianming Zheng, Juyong Zhang, Jianfei Cai, Tat-Jen Cham. Recovering surface details under general unknown illumination using shading and coarse multi-view stereo. CVPR, 2014 [ieee, local]
• Anran Wang, Jiwen Lu, Gang Wang, Jianfei Cai, Tat-Jen Cham, Multi-modal unsupervised feature learning for RGB-D scene labeling. ECCV, 2014. [springer, local]
• Anran Wang, Jiwen Lu, Jianfei Cai, Gang Wang, Tat-Jen Cham, Estimating spatial layout of rooms from RGB-D videos. MMSP, 2014. Top 10% paper. [ieee, local]
• Cédric Fleury, Tiberiu Popa, Tat-Jen Cham, Henry Fuchs, Merging live and pre-captured data to support full 3D head reconstruction for telepresence. Eurographics, 2014. Short paper. [eg, local]
• Yi Huang, Dong Xu, Tat-Jen Cham, Face and human gait recognition using image-to-class distance. IEEE T-CSVT, 2010. [ieee, local]
• Dong Xu, Tat-Jen Cham, Shuicheng Yan, Lixin Duan, Shih-Fu Chang, Near duplicate identification with spatially aligned pyramid matching. IEEE T-CSVT, 2010. [ieee, local]
• Tat-Jen Cham, Arridhana Ciptadi, Wei-Chian Tan, Minh-Tri Pham, Liang-Tien Chia, Estimating camera pose from a single urban ground-view omnidirectional image and a 2D building outline map. CVPR, 2010. CVPR oral paper. [ieee, local]
• Minh-Tri Pham, Yang Gao, Viet-Dung Hoang, Tat-Jen Cham, Fast polygonal integration and its application in extending Haar-like features to improve object detection. CVPR, 2010. [ieee, local]
• Minh-Tri Pham, V-D. D. Hoang, Tat-Jen Cham, Detection with multi-exit asymmetric boosting. CVPR, 2008. [ieee, local]
• Dong Xu, Tat-Jen Cham, Shuicheng Yan, Shih-Fu Chang, Near duplicate image identification with patially aligned pyramid matching, CVPR, 2008. [ieee, local]
• Minh-Tri Pham, Tat-Jen Cham, Fast training and selection of Haar features using statistics in boosting-based face detection. ICCV, 2007. ICCV oral paper. PREMIER 2nd best student paper prize (among all Singapore research papers in field of pattern recognition). [ieee, local]
• Minh-Tri Pham, Tat-Jen Cham, Online learning asymmetric boosted classifiers for object detection. CVPR, 2007. CVPR oral paper. [ieee, local]
• Xi Chen, Tat-Jen Cham, High distortion and non-structural image matching via feature co-occurrence, CVPR, 2007. [ieee, local]
• Michael S. Brown, Peng Song, Tat-Jen Cham, Image pre-conditioning for out-of-focus projector blur. CVPR, 2006. [ieee, local]
• Minh-Tri Pham, Tat-Jen Cham, Detection caching for faster object detection. ICCV Workshop PHI, 2005. [local]
• Peng Song, Tat-Jen Cham, A theory for photometric self-calibration of multiple overlapping projectors and cameras. CVPR Workshop PROCAMS, 2005. Best paper prize. [ieee, local]
• Xi Chen, Tat-Jen Cham, Learning feature distance measures for image correspondences. CVPR, 2005. [ieee, local]
• Tat-Jen Cham, James M. Rehg, Rahul Sukthankar, Gita Sukthankar, Shadow elimination and occluder light suppression for multi-projector displays. CVPR, 2003. [ieee, local]
• Tat-Jen Cham, Shyam Krishnamoorthy, Michael J. Jones, Analogous view transfer for gaze correction in video sequences, ICARCV, 2002. [ieee, local]
• David E. DiFranco, Tat-Jen Cham, James M. Rehg, Reconstruction of 3-D figure motion from 2-D correspondences. CVPR, 2001. CVPR oral paper. [ieee, local]
• Rahul Sukthankar, Tat-Jen Cham, Gita Sukthankar, Dynamic shadow elimination for multi-projector displays. CVPR, 2001. [ieee, local]
• Tat-Jen Cham, Roberto Cipolla, Automated b-spline curve representation incorporating MDL and error-minimizing control point insertion strategies, IEEE TPAMI, 21(1): 49-53, 1999. [ieee]
• Tat-Jen Cham, James M. Rehg, A multiple hypothesis approach to figure tracking. CVPR, 1999. CVPR oral paper. [ieee, local]
• Tat-Jen Cham, James M. Rehg, Dynamic feature ordering for efficient registration. ICCV, 1999. ICCV oral paper. [ieee, local]
• Vladimir Pavlovic, James M. Rehg, Tat-Jen Cham, Kevin P. Murphy, A dynamic Bayesian network approach to figure tracking using learned dynamic models. ICCV, 1999. ICCV oral paper. [ieee, local]
• Tat-Jen Cham, Roberto Cipolla, A statistical framework for long-range feature matching in uncalibrated image mosaicing. CVPR, 1998. [ieee, local]
• Tat-Jen Cham, Roberto Cipolla, Stereo coupled active contours. CVPR, 1997. CVPR oral paper. [ieee, local]
• Tat-Jen Cham, Roberto Cipolla, Geometric saliency of curve correspondances and grouping of symmetric contours, ECCV, 1996. ECCV best paper prize. [springer, local]
• Tat-Jen Cham, Roberto Cipolla, Skewed symmetry detection through local skewed symmetries. BMVC, 1994. BMVC best science paper prize. Also as article in IVC. [scd, local]