I am a Professor in the School of Computing Science at SFU, and also Vice President of AI and R&D at Augmenta.
At Augmenta, I lead the company's effort in developing the most advanced AI models and tools for efficient and sustainable building designs.
More broadly, we are exploring spatial and functional intelligence to tackle challenges in the physical world and contributing to the R&D ecosystem for physical AI.
[pinned] Thrilled to join Augmenta as VP of AI and R&D in August 2025. I will lead the company's effort in developing the most advanced AI models and tools for efficient and sustainable building designs. Please see official press release.
[pinned] Inducted into the ACM SIGGRAPH Academy, class of 2025, for technical contributions in spectral and learning-based methods for geometric modeling. See SFU's coverage on this.
[new] April 22, 2026: Our paper ATOP has been accepted to ACM Transaction on Graphics. It is a novel few-shot method based on motion personalization to articulate a static 3D object with respect to a part and its motion as prescribed in a text prompt. Congratulations Aditya!
[new] April 19, 2026: Fresh from talks at 3DV 2026 in Vancouver and CDFAM 2026 in Barcelona (read an interview piece), I shared on an Augmenta blog, why Spatial and Functional AI, not general-purpose LLMs, define the real frontier for construction, and why 2026 may be the industry's inflection point. More generally, my two talks there, as well as a third talk at Computational Visual Media 2026 in Seoul, discussed the role Functional AI plays in 3D generation and other applications in the physical domain.
[new] April 8: Congratulations to Kai Wang who is set to start as an Assistant Professor at Shanghai Tech! Kai has worked with me as an Amazon Scholar for two years and then as a visiting scholar in the GrUVi lab for about a year. We have many collaborative projects together!
[new] March 22, 2026: Check out my recent LinkedIn post on building Foundation Model for 3D Building and Construction, following our panel discussion at 3DV 2026.
December 1, 2025: Two papers accepted to 3DV 2026, ACT-R for adaptive trajectory planning for single-view 3D reconstruction and HiT for Hierarchical Transformers, and one paper provisionally accepted to ACM Trans. on Graphics. Stay tuned! Congratulations to Mingrui, Yizhi, and Aditya!
September 25: Three papers accepted to SIGGRAPH Asia 2025: a) In-2-4D for 4D interpolation from monocular images, b) ASIA for Adaptive 3D Segmentation from Image Annotations, and c) ART-DECO for text-guided 3D detailization, in colloboration with Adobe Research. Congrats to Sai Raj, Sauradip, and Qimin!
August 15, 2025: SIGGRAPH 2025 has concluded in Vancouver, Canada, today. As the Technical Papers Chair, I am so proud of the outstanding papers program we have put together. We set a record for both the number of submissions (972) and also the accepted papers (306)! See you all in LA for SIGGRAPH 2026.
May 28, 2025: Thank YOU, Adobe, for your continued and generous support for my research through GIFT funds!
May 9, 2025: Two papers accepted to SIGGRAPH 2025, MASH and HoLa, both on 3D representation learning; see details on publication page.
April 2, 2025: Our CVPR 2025 paper, ArcPro, a novel learning framework built on architectural programs to recover structured 3D abstractions from highly sparse and low-quality point clouds, has been selected as a Highlight paper!
March 29, 2025: The SIGGRAPH 2025 Technical Papers Committee (TPC) meeting has just concluded at the SFU Harbour Center Downtown Campus. Here is composite photo of the TPC. A TPC Workshop was also held after the meeting.
December 6, 2024: SIGGRAPH Asia 2024 has concluded in Tokyo, Japan. I was the Technical Papers Assistant Chair, helping Papers Chair Ariel Shamir.
October 11, 2024: I delivered a keynote talk on "Why is 3D Generation Hard?" at ChinaGraph 2024, held in Yellow Mountain.
September 27, 2024: I am serving on the Science Advisory Board (SAB) of Max Planck Institute (MPI) for Informatics on a six-year term.
July 1, 2024: Three papers accepted to ECCV 2024 (see papers page for more details). Congrats to Ruiqi, Qimin, and Fenggen!
June 18, 2024: Introducing our CVPR 2024 paper on Slice3D, a completely new way of solving single-view 3D reconstruction, now with code (also see video). Instead of going from single- to multi-view (and then say a NeRF), we advocate going from single-view to multi-slice images. Our key observation is that slicing offers the best way to reveal occluded structures: in the limit, slicing completely reveals everything while the same cannot be said about multi-view reasoning. All Slice3D results were produced by networks trained on a single Nvidia A40 GPU, with an inference time less than 20 seconds.
June 1, 2024: Congrats to Zhiqin Chen who is the winner of the 2024 Governor General's Gold Medal at SFU's convocation for achieving the highest academic standing upon graduation from a doctoral degree program, the 2024 Alain Fournier Award for the best Ph.D. dissertation in computer graphics in Canada, and a winner of the 2024 Eurographics PhD Award for Best PhD Thesis. The Alain Fournier Award is the second won by an SFU graduate; the first was Ibraheem Alhashim in 2015. The Eurographics award is a first.
April 23, 2024: Congrats to Sai Raj who successfully defended his Masters thesis on "EASI-Tex: Edge-Aware Mesh Texturing from Single Image" with a "Pass As Is". He will start his PhD in our group in summer 2024.
April 5, 2024: Congrats to Fenggen who successfully defended his PhD thesis on "Learning Structured Representations of 3D CAD Models" with a "Pass As Is".
April 1, 2024: Four papers accepted to SIGGRAPH 2024, including two journals. Congrats to Yilin, Zhiqin, Jingyu, and especially Sai Raj on his first SIGGRAPH paper! Details can be found on my publication page.
December 26, 2023: Our "Virtual Try-On" workshop, another Amazon-led effort after the ICCV 2023 3DVeComm Workshop in Paris, has been accepted to CVPR 2024!
September 26, 2023: We will be presenting two papers at ICCV 2023 in Paris, two papers at NeurIPS 2023 in New Orleans, and four papers at SIGGRAPH Asia in Sydney, Australia! Congratulations to Maham, Fenggen, Qimin,
Aditya, Yizhi, Akshay, Hang, and Zhiqin, along with all my collaborators.
June 17, 2023: Congratulations to Akshay and Zhiqin for their successful PhD defenses yesterday. Both theses and defenses received the distinction of "pass as is"! I am proud of you!
April 6, 2023: I delivered a keynote talk on "An Evolution of Learning Neural Implicit Representations for 3D Shapes" at Computational Visual Media (CVM) 2023.
March 20, 2023: Welcome Yizhi Wang who has started his postdoc in 2023. Yizhi obtained his PhD from PKU in 2022 and before arriving in Vancouver, he made a short visit to Shenzhen University and worked there on a collaborative project on neural 3D reconstruction, ARO-Net, which will be presented at CVPR 2023.
There is a pleasure in the pathless woods;
There is a rapture on the lonely shore;
There is society, where none intrudes,
By the deep sea, and music in its roar;
I love not man the less, but Nature more.