Score Jacobian Chaining: Lifting Pretrained 2D Diffusion Models for 3D Generation

pals-ttic/sjc 1 Dec 2022

We propose to apply chain rule on the learned gradients, and back-propagate the score of a diffusion model through the Jacobian of a differentiable renderer, which we instantiate to be a voxel radiance field.

150
2.60 stars / hour

ExtremeBERT: A Toolkit for Accelerating Pretraining of Customized BERT

extreme-bert/extreme-bert 30 Nov 2022

In this paper, we present ExtremeBERT, a toolkit for accelerating and customizing BERT pretraining.

Molecular System Prediction Sentence Classification

172
1.84 stars / hour

Zero-Shot Image Restoration Using Denoising Diffusion Null-Space Model

wyhuai/ddnm 1 Dec 2022

Most existing Image Restoration (IR) models are task-specific, which can not be generalized to different degradation operators.

Colorization Deblurring +3

68
1.30 stars / hour

TorchScale: Transformers at Scale

microsoft/torchscale 23 Nov 2022

Large Transformers have achieved state-of-the-art performance across many tasks.

Language Modelling Machine Translation +1

903
1.25 stars / hour

Compressing Volumetric Radiance Fields to 1 MB

algohunt/vqrf 29 Nov 2022

Approximating radiance fields with volumetric grids is one of promising directions for improving NeRF, represented by methods like Plenoxels and DVGO, which achieve super-fast training convergence and real-time rendering.

Model Compression Neural Rendering +1

120
1.16 stars / hour

Mixed Neural Voxels for Fast Multi-view Video Synthesis

fengres/mixvoxels 1 Dec 2022

In this paper, we present a novel method named MixVoxels to better represent the dynamic scenes with fast training speed and competitive rendering qualities.

59
1.16 stars / hour

DiffusionBERT: Improving Generative Masked Language Models with Diffusion Models

hzfinfdu/diffusion-bert 28 Nov 2022

We present DiffusionBERT, a new generative masked language model based on discrete diffusion models.

Denoising Language Modelling +1

83
1.01 stars / hour

Multiresolution Textual Inversion

giannisdaras/multires_textual_inversion 30 Nov 2022

We extend Textual Inversion to learn pseudo-words that represent a concept at different resolutions.

53
0.72 stars / hour

DAMO-YOLO : A Report on Real-Time Object Detection Design

tinyvision/damo-yolo 23 Nov 2022

In this report, we present a fast and accurate object detection method dubbed DAMO-YOLO, which achieves higher performance than the state-of-the-art YOLO series.

Neural Architecture Search object-detection +1

249
0.71 stars / hour

SuperFusion: Multilevel LiDAR-Camera Fusion for Long-Range HD Map Generation and Prediction

haomo-ai/superfusion 28 Nov 2022

To this end, we propose a novel network named SuperFusion, exploiting the fusion of LiDAR and camera data at multiple levels.

Autonomous Driving

91
0.71 stars / hour