Denys Iliash (@iliashdo) profile picture

PhD student @sfu_cs_3dlg

Joined February 2026
Photo by Denys Iliash (@iliashdo)Photo by Denys Iliash (@iliashdo)Photo by Denys Iliash (@iliashdo)Photo by Denys Iliash (@iliashdo)
Denys Iliash retweeted
Rule #1 of 3DGS capture: don't touch anything! Open a door and it messes up your whole scene. ๐Ÿšช But what if you do? ๐’๐ฐ๐ข๐ญ๐œ๐ก๐’๐ฉ๐ฅ๐š๐ญ (SIGGRAPH Asia 2026) turns what you touched into switches you can flip ๐Ÿ‘‡ switchsplat.github.io
7
18
7
200
14,924
Denys Iliash retweeted
Excited to share GATOR ๐ŸŠ! From a few casual photos (clutter, occlusion, estimated cameras), we reconstruct complete, textured 3D objects placed back in their scene. A generative model builds the asset, then an agent refines it. research.nvidia.com/labs/lprโ€ฆ
Casual photos in, simulation-ready 3D objects out! Introducing ๐ŸŠGATOR๐ŸŠ, generative + agentic 3D object reconstruction. Here, humanoids interact with GATOR-reconstructed furniture [1/n] Website: research.nvidia.com/labs/lprโ€ฆ Paper: arxiv.org/abs/2610.11215
1
5
1
11
701
Denys Iliash retweeted
Actually there was some more to explore! ๐Ÿ’ƒ @NeurIPSConf #Neurips2026 See you at the conference!
Happy to see these papers accepted #Neurips2026 ๐ŸŽŠ ๐ŸŽŠ ๐ŸŽŠ Please come and find us at the conference! More details & links in ๐Ÿงต
3
7
389
Denys Iliash retweeted
Happy to see these papers accepted #Neurips2026 ๐ŸŽŠ ๐ŸŽŠ ๐ŸŽŠ Please come and find us at the conference! More details & links in ๐Ÿงต
2
7
4
31
3,813
Denys Iliash retweeted
3D models can look right and still fall apart. Introducing Functionalization: graph completion adds missing structure and connectors to rectify motion and make models work. SIGGRAPH Asia 2026 Paper, code, data available at: mingrui-zhao.github.io/Functโ€ฆ
11
53
2
476
31,105
Denys Iliash retweeted
1/8 Good morning Malmรถ ๐Ÿ‡ธ๐Ÿ‡ช! #ECCV2026 Have you wondered how far we are from building interactable 3D worlds? Come join our FAI workshop and hear the worldโ€™s leading researchersโ€™ opinions! Today, 9 Sept ยท 14:00โ€“17:35 CEST Malmรถ Arena ยท Palissad East Talk details follow!
1
4
1
18
1,473
Join us for the Functionality, Articulation & Interaction workshop at #ECCV2026 tomorrow! Our incredible lineup: - Andrea Vedaldi (@Oxford_VGG) - Wei-Chiu Ma (@weichiuma) - Evangelos Kalogerakis (@EvangelosKalog1) - Angela Dai (@angelaqdai) - Mikaela Angelina Uy (@mikacuy)
1
6
3
11
3,999
Denys Iliash retweeted
1/5 From one physical digital twin to 1,000+ interactive users โ€” on a single GPU. ๐Ÿš€ Introducing Boba ๐Ÿง‹, our #ECCV2026 system for high-throughput batched physical digital twins. Come try it live! ๐Ÿ“… Sep 11, 12:30โ€“17:00 ๐Ÿ“ Demo 4 ๐Ÿงต๐Ÿ‘‡
๐Ÿš€ How can we create interactive Physical Digital Twins from videos? Thrilled to share our latest work: PhysTwin! ๐ŸŒŸ Using inverse physics optimization, we generate photo-realistic, physically accurate, and real-time interactive virtual replicas. ๐Ÿ”ฅ ๐Ÿ”—jianghanxiao.github.io/phystโ€ฆ
1
4
1
38
5,757
Denys Iliash retweeted
Super proud of our work. You can read more about it here: ๐ŸŒ serchirag.github.io/roms-imlโ€ฆ ๐Ÿ“œ arxiv.org/pdf/2607.19332
Diffusion/flow matching is a go-to generative AI paradigm, but it's slow, sample inefficient and complicated. Do we really need all this complexity? We design a small and simple one-step model, ROMS-IMLE, which attains an FID of 2.56 on ImageNet. Joint w/ @researchirag 1/6
5
55
8,741
I will be giving two workshop talks at #ECCV2026 (stay tuned) and opening a third on Functionality, Articulation, and Interaction (diliash.github.io/fai_eccv_wโ€ฆ). Please also check out our oral paper on PADFormer (arxiv.org/abs/2608.04210) on Friday.
We are heading to #ECCV2026 in Malmรถ ๐Ÿ‡ธ๐Ÿ‡ช Come find us there Sept 8โ€“13! ๐ŸŽŠ @eccvconf
4
8
661
Denys Iliash retweeted
We are heading to #ECCV2026 in Malmรถ ๐Ÿ‡ธ๐Ÿ‡ช Come find us there Sept 8โ€“13! ๐ŸŽŠ @eccvconf
6
4
19
7,595
Denys Iliash retweeted
Happy to share our work accepted to @icmlconf ๐Ÿฅณ๐ŸŽ‰๐ŸŽ‰๐ŸŽ‰๐ŸŽ‰ See you in Korean๐Ÿ‡ฐ๐Ÿ‡ท Links & details in ๐Ÿงต
1
8
1
21
1,756
Denys Iliash retweeted
๐Ÿ“ข Excited to share our ๐˜Œ๐˜ถ๐˜ณ๐˜ฐ๐˜จ๐˜ณ๐˜ข๐˜ฑ๐˜ฉ๐˜ช๐˜ค๐˜ด ๐˜š๐˜›๐˜ˆ๐˜™ 2026 paper: ๐—”๐—ฑ๐˜ƒ๐—ฎ๐—ป๐—ฐ๐—ฒ๐˜€ ๐—ถ๐—ป ๐—ก๐—ฒ๐˜‚๐—ฟ๐—ฎ๐—น ๐Ÿฏ๐—— ๐— ๐—ฒ๐˜€๐—ต ๐—ง๐—ฒ๐˜…๐˜๐˜‚๐—ฟ๐—ถ๐—ป๐—ด: ๐—” ๐—ฆ๐˜‚๐—ฟ๐˜ƒ๐—ฒ๐˜† We organize the rapidly growing field of Neural 3D Mesh Texturing, covering how learning-based methods generate, transfer, complete, and refine texture and material appearance on 3D meshes. We cover: ๐Ÿงฑ ๐˜๐˜ฐ๐˜ถ๐˜ฏ๐˜ฅ๐˜ข๐˜ต๐˜ช๐˜ฐ๐˜ฏ๐˜ด: Mesh geometry, UV mapping, differentiable rendering, PBR materials, and neural generative models. ๐Ÿงญ ๐˜”๐˜ฆ๐˜ต๐˜ฉ๐˜ฐ๐˜ฅ ๐˜ง๐˜ข๐˜ฎ๐˜ช๐˜ญ๐˜ช๐˜ฆ๐˜ด: GAN-based methods, CLIP-guided and diffusion-based optimization, iterative painting, synchronized multi-view generation, and feed-forward approaches. ๐Ÿ“Š ๐˜Œ๐˜ท๐˜ข๐˜ญ๐˜ถ๐˜ข๐˜ต๐˜ช๐˜ฐ๐˜ฏ ๐˜ข๐˜ฏ๐˜ฅ ๐˜ฐ๐˜ถ๐˜ต๐˜ญ๐˜ฐ๐˜ฐ๐˜ฌ: Datasets, evaluation metrics, applications, limitations, and future research directions. ... and much more. We also created a project page with a growing list of neural mesh texturing papers, making it easier to explore recent work in this fast-moving field. ๐Ÿ“ฐ Paper: arxiv.org/abs/2606.00137 ๐ŸŒŽ Project Page: sairajk.github.io/neural-mesโ€ฆ Suggestions, corrections, and missing papers are very welcome! Joint work with my supervisors, @richardzhangsfu and @arash_mham. #ComputerGraphics #3DVision #GenerativeAI #NeuralRendering #MeshTexturing #TextureSynthesis #DiffusionModels #GANs #VLM #3DAssets #PBR #DigitalContentCreation #GameDev #VFX #XR #DigitalHumans #Eurographics #EurographicsSTAR #CGF #Rendering
22
94
5,725
Working on perception for embodied AI? Interactive objects/scenes? Physical grounding? Submit to our #ECCV2026 workshop! ๐Ÿ”— diliash.github.io/fai_eccv_wโ€ฆ
1/ ๐Ÿ“ข Announcing the FAI Workshop @ ECCV 2026 in Malmรถ ๐Ÿ‡ธ๐Ÿ‡ช 3D generative AI makes objects that look stunning โ€” but can they move, obey physics, and actually be interacted with? That gap is what FAI is about. ๐Ÿงต #ECCV2026 #ComputerVision #3DVision #GenerativeAI #Robotics
1
1
4
950
Denys Iliash retweeted
What senses does embodied AI need beyond vision? Join us at Sense of Space Workshop @CVPR โ€” a full-day workshop on multi-sensory modeling for embodied intelligence. ๐Ÿ“… June 3rd ๐Ÿ“ Mile High 2C, Denver ๐Ÿ–ผ Posters: Hall A #275โ€“282 Featuring invited talks from leading researchers across robotics, vision, sensing, and embodied AI. @NimaFazeli7 @notmahi @mapo1 @wojmatusik Christian Theobalt @mangahomanga @Boyiliee @yswhynot @LingjieLiu1 @pliang279 @Ismini_L Website: sense-of-space.github.io/ #CVPR2026 #EmbodiedAI #Robotics #MultimodalAI #TactileSensing #SpatialIntelligence Powered by the amazing team! @RaoFu79761158 @LiGuankfd2 @alex_kai2020 Kun He @tomhodan Ergys Ristani Jessica Yin @AntheaYLi @yining_hong Devin Murphy Ray Song @xyz2maureen @ericyi0124 Qi Ye @YunzhuLiYZ @haoshu_fang @ruoshi_liu Vatsal Mehta @LuoYiyue @MengyuLearner
8
1
26
3,932
Introducing ๐—”๐—ฟ๐˜๐—ถ๐˜ƒ๐—ฒ๐—ฟ๐˜€๐—ฒ dataset: 5.4K articulated objects for embodied AI ๐Ÿค– โ€ข 88 categories โ€ข Functional part segmentation + articulation โ€ข Per-part material + mass โ€ข Procedural interiors #CVPR2026 โ€” Poster 164 Session 2 & ActiVis Workshop Website + paper below ๐Ÿงต
1
10
1
27
3,052
Artiverse enables interactive scene generation, training of manipulation policies and more!
1
2
187