Next upHack for Humanity: San Francisco (powered by Google Gemini)Sat, Sep 19 · 15:45 PDT

Notify meSee schedule

Sign in Subscribe

Next upHack for Humanity: San Francisco (powered by Google Gemini)Sat, Sep 19 · 15:45 PDT

Notify meSee schedule

Back to Dmytro Spodarets

Dmytro Spodarets

Articles by Dmytro Spodarets

159 items

Scalable Diffusion Models with Transformers
In this work, the researchers explore a new class of diffusion models based on the transformer architecture; train latent diffusion models, replacing the U-Net backbone with a transformer that operates on latent patches; and analyze the scalability of Diffusion Transformers (DiTs).
Jan 3, 2023
NeRF-Art: Text-Driven Neural Radiance Fields Stylization
Neural radiance fields (NeRF) enable high-quality novel view synthesis. Editing NeRF, however, remains challenging. In this paper, the authors present NeRF-Art, a text-guided NeRF stylization approach that manipulates the style of a pre-trained NeRF model with a single text prompt.
Dec 30, 2022
ECON: Explicit Clothed humans Obtained from Normals
ECON combines the best aspects of implicit and explicit surfaces to infer high-fidelity 3D humans, even with loose clothing or in challenging poses. ECON is more accurate than the state of the art. Perceptual studies also show that ECON’s perceived realism is better by a large margin.
Dec 27, 2022
Data Phoenix Digest - ISSUE 62
AI image generator, data versioning for ML in Airflow, the illustrated stable diffusion, into the transformer, building Airbnb categories with ML and Human-in-the-Loop, novel view synthesis with diffusion models, RANA, UDE, 3DHumanGAN, courses, books, and more.
Dec 27, 2022
3DHumanGAN: Towards Photo-realistic 3D-Aware Human Image Generation
3DHumanGAN is a 3D-aware generative adversarial network (GAN) that synthesizes images of full-body humans with consistent appearances under different view-angles and body-poses. The model is adversarially learned from a collection of web images needless of manual annotation.
Dec 26, 2022
Novel View Synthesis with Diffusion Models
3DiM is a diffusion model for 3D novel view synthesis from as few as a single image. Comparing it to the SRN ShapeNet dataset, it is clear that 3DiM's generated videos from a single view achieve much higher fidelity while being approximately 3D consistent.
Dec 23, 2022
UDE: A Unified Driving Engine for Human Motion Generation
Unified Driving Engine (UDE) is the first unified driving engine that enables generating human motion sequences from natural language or audio sequences. It can support both text-driven and audio-driven human motion generation.
Dec 21, 2022
RANA: Relightable Articulated Neural Avatars
RANA is a relightable and articulated neural avatar for the photorealistic synthesis of humans under arbitrary viewpoints, body poses, and lighting. It is a novel framework to model humans while disentangling their geometry, texture, and lighting environment from monocular RGB videos.
Dec 18, 2022
Data Phoenix Digest - ISSUE 61
Webinar "Vertex AI Pipelines infrastructure with Terraform", data version control with DVC and Git, the 5 stages of ML validation, 10 quick pandas tricks, InstructPix2Pix, DAMO-YOLO, ReFace, DiffusionInst, DiffusionBERT, and more.
Dec 17, 2022
Data Phoenix Digest - ISSUE 60
Webinar "Vertex AI Pipelines infrastructure with Terraform", bringing GitOps to ML with dstack, “You Can’t Predict the Errors of Your Model”… Or Can You?, time series analysis introduction, DeepAR, DiffusionDet, Galactica, Versatile Diffusion, CodeGen, and more.
Dec 9, 2022
ULNeF: Untangled Layered Neural Fields for Mix-and-Match Virtual Try-On
Recent advances in neural models have shown excellent results for virtual fitting tasks (VTO), where a 3D representation of a garment is deformed to fit the target body shape. However, existing solutions are limited to a single layer of clothing and cannot solve the combinatorial complexity of mixing different types of clothing. To address this limitation, scientists present non-overlapping layered neural fields, ULNeFs, which solve the multi object interaction problem using implicit object rep
Nov 19, 2022
Data Phoenix Digest - ISSUE 59
Efficiently scaling transformer inference, MLOps pipeline with GitLab in minutes, monitoring ML models with Vertex AI, scaling instruction-finetuned language models, Colossal-AI, InternImage, AnimeRun, PhaseAug, and more.
Nov 18, 2022