Eric Chan
@ericryanchan
Followers
365
Following
37
Media
6
Statuses
29
Introducing pi-GAN: Periodic Implicit GANs for 3D-Aware Image Synthesis. Trained on unlabeled images, π-GAN generates 3D representations and synthesizes images from arbitrary poses. Website: @monteiroamarco Petr Kellnhofer @GordonWetzstein @jiajunwu_cs
2
40
177
RT @isskoro: In the past 1.5 weeks, there appeared 2 papers by 2 different research groups which develop the exactly same (and embarrassing….
0
57
0
Some cool work led by @prime_cai showing how you can adapt a diffusion model for image-to-image tasks using data generated by itself. My favorite examples are of “decomposition”, but it’s useful for other image2image tasks like relighting and character-consistent generation too!
Sharing something exciting we've been working on as a Thanksgiving gift: Diffusion Self-Distillation (DSD), which redefines zero-shot customized image generation using FLUX. DSD is like DreamBooth, but zero-shot/training-free. It works across any input subject and desired
0
2
15
RT @boyang_deng: Thought about generating realistic 3D urban neighbourhoods from maps, dawn to dusk, rain or shine? Putting heavy snow on t….
0
19
0
RT @isskoro: This paper has received significantly less attention than it deserves, so let me shed a bit more light on it and describe why….
0
228
0
RT @taiyasaki: 📢📢📢 thrilled to announce "𝟒𝐃-𝐟𝐲: 𝐓𝐞𝐱𝐭-𝐭𝐨-𝟒𝐃 𝐆𝐞𝐧𝐞𝐫𝐚𝐭𝐢𝐨𝐧 𝐔𝐬𝐢𝐧𝐠 𝐇𝐲𝐛𝐫𝐢𝐝 𝐒𝐜𝐨𝐫𝐞 𝐃𝐢𝐬𝐭𝐢𝐥𝐥𝐚𝐭𝐢𝐨𝐧 𝐒𝐚𝐦𝐩𝐥𝐢𝐧𝐠". W….
0
76
0
RT @KyleSargentAI: I’m really excited to finally share our new paper “ZeroNVS: Zero-shot 360-degree View Synthesis from a Single Real Image….
0
55
0
RT @MattNiessner: Diffusion models are awesome! . Check out our survey on 𝐃𝐢𝐟𝐟𝐮𝐬𝐢𝐨𝐧 𝐌𝐨𝐝𝐞𝐥𝐬 𝐟𝐨𝐫 𝐕𝐢𝐬𝐮𝐚𝐥 𝐂𝐨𝐦𝐩𝐮𝐭𝐢𝐧𝐠! We give an introduction to….
0
88
0
RT @jjpark3D: Eric Chan @ericryanchan will be presenting our #ICCV2023 work GeNVS at the "Generative AI 1" Oral session today (Oct. 4th 0….
0
2
0
RT @songyoupeng: Given a single image, have you ever dreamed about how it would look like if you fly into it? We present DiffDreamer for 3D….
0
4
0
RT @vincesitzmann: Introducing “FlowCam: Training Generalizable 3D Radiance Fields w/o Camera Poses via Pixel-Aligned Scene Flow”! We train….
0
94
0
RT @luminohope: We also present another paper at @SIGGRAPH 2023 on neural implicit 3D Morphable Models that can be used to create a dynamic….
0
41
0
RT @luminohope: AI-driven 3D lifting has huge potential! Choose your favorite AI tool to generate/customize an avatar and bring it to life….
0
100
0
RT @hyunjik11: We're organizing an #ICLR2023 workshop titled:.🌟Neural Fields across Fields: Methods and Applications of Implicit Neural Rep….
sites.google.com
News
0
24
0
RT @alexwbergman: We are excited to present our work at #NeurIPS22 on Generative Neural Articulated Radiance Fields! In this paper, we buil….
0
40
0
RT @JunGao33210520: Excited to share our #NeurIPS2022 @NVIDIAAI work GET3D, a generative model that directly produces explicit textured 3D….
0
558
0
RT @luminohope: also if you come to our poster early, we (@ericryanchan, Matthew, @shalinidemello ) will show a live 3D visualizer demo run….
0
2
0
RT @luminohope: If you are at #CVPR2022, please come see "EG3D" Friday morning .𝐓𝐚𝐥𝐤: 𝟗:𝟑𝟎𝐚𝐦~ @ 𝐆𝐫𝐞𝐚𝐭 𝐇𝐚𝐥𝐥 𝐀-𝐃.𝐏𝐨𝐬𝐭𝐞𝐫𝐬 (𝟏𝟑𝐚) 𝟏𝟎:𝟎𝟎-𝟏𝟐:𝟑𝟎𝐩𝐦….
0
17
0
RT @vincesitzmann: Introducing "Light Field Networks: Neural Scene Representations with Single-Evaluation Rendering"!. .
0
122
0
RT @jnpmartel: Our new work on scaling up neural representations is out! Adaptive coordinate networks (ACORN) can be trained to represent h….
0
38
0
RT @MonteiroAMarco: Happy π day! How many pies would @ericryanchan and I have to eat to get enough images to train pi-GAN on pies?.https:/….
0
4
0