EPIC Fields: Marrying 3D Geometry and Video Understanding

Neural rendering is fuelling a unification of learning, 3D geometry and video understanding that has been waiting for more than two decades. Progress, however, is still hampered by a lack of suitable datasets and benchmarks. To address this gap, we introduce EPIC Fields, an augmentation of EPIC-KITCHENS with 3D camera information. Like other datasets for neural rendering, EPIC Fields removes the complex and expensive step of reconstructing cameras using photogrammetry, and allows researchers to focus on modelling problems. We illustrate the challenge of photogrammetry in egocentric videos of dynamic actions and propose innovations to address them. Compared to other neural rendering datasets, EPIC Fields is better tailored to video understanding because it is paired with labelled action segments and the recent VISOR segment annotations. To further motivate the community, we also evaluate two benchmark tasks in neural rendering and segmenting dynamic objects, with strong baselines that showcase what is not possible today. We also highlight the advantage of geometry in semi-supervised video object segmentations on the VISOR annotations. EPIC Fields reconstructs 96% of videos in EPICKITCHENS, registering 19M frames in 99 hours recorded in 45 kitchens.

Viewset Diffusion: (0-)Image-Conditioned 3D Generative Models from 2D Data

We present Viewset Diffusion: a framework for training image-conditioned 3D generative models from 2D data. Image-conditioned 3D generative models allow us to address the inherent ambiguity in single-view 3D reconstruction. Given one image of an object, there is often more than one possible 3D volume that matches the input image, because a single image never captures all sides of an object. Deterministic models are inherently limited to producing one possible reconstruction and therefore make mistakes in ambiguous settings. Modelling distributions of 3D shapes is challenging because 3D ground truth data is often not available. We propose to solve the issue of data availability by training a diffusion model which jointly denoises a multi-view image set.We constrain the output of Viewset Diffusion models to a single 3D volume per image set, guaranteeing consistent geometry. Training is done through reconstruction losses on renderings, allowing training with only three images per object. Our design of architecture and training scheme allows our model to perform 3D generation and generative, ambiguity-aware single-view reconstruction in a feed-forward manner. Project page: szymanowiczs.github.io/viewset-diffusion.

Contrastive Lift: 3D Object Instance Segmentation by Slow-Fast Contrastive Fusion

Instance segmentation in 3D is a challenging task due to the lack of large-scale annotated datasets. In this paper, we show that this task can be addressed effectively by leveraging instead 2D pre-trained models for instance segmentation. We propose a novel approach to lift 2D segments to 3D and fuse them by means of a neural field representation, which encourages multi-view consistency across frames. The core of our approach is a slow-fast clustering objective function, which is scalable and well-suited for scenes with a large number of objects. Unlike previous approaches, our method does not require an upper bound on the number of objects or object tracking across frames. To demonstrate the scalability of the slow-fast clustering, we create a new semi-realistic dataset called the Messy Rooms dataset, which features scenes with up to 500 objects per scene. Our approach outperforms the state-of-the-art on challenging scenes from the ScanNet, Hypersim, and Replica datasets, as well as on our newly created Messy Rooms dataset, demonstrating the effectiveness and scalability of our slow-fast clustering method.

DynamicStereo: Consistent Dynamic Depth from Stereo Videos

We consider the problem of reconstructing a dynamic scene observed from a stereo camera. Most existing methods for depth from stereo treat different stereo frames independently, leading to temporally inconsistent depth predictions. Temporal consistency is especially important for immersive AR or VR scenarios, where flickering greatly diminishes the user experience. We propose DynamicStereo, a novel transformer-based architecture to estimate disparity for stereo videos. The network learns to pool information from neighboring frames to improve the temporal consistency of its predictions. Our architecture is designed to process stereo videos efficiently through divided attention layers. We also introduce Dynamic Replica, a new benchmark dataset containing synthetic videos of people and animals in scanned environments, which provides complementary training and evaluation data for dynamic stereo closer to real applications than existing datasets. Training with this dataset further improves the quality of predictions of our proposed DynamicStereo as well as prior methods. Finally, it acts as a benchmark for consistent stereo methods.

Farm3D: Learning Articulated 3D Animals by Distilling 2D Diffusion

We present Farm3D, a method to learn category-specific 3D reconstructors for articulated objects entirely from "free" virtual supervision from a pre-trained 2D diffusion-based image generator. Recent approaches can learn, given a collection of single-view images of an object category, a monocular network to predict the 3D shape, albedo, illumination and viewpoint of any object occurrence. We propose a framework using an image generator like Stable Diffusion to generate virtual training data for learning such a reconstruction network from scratch. Furthermore, we include the diffusion model as a score to further improve learning. The idea is to randomise some aspects of the reconstruction, such as viewpoint and illumination, generating synthetic views of the reconstructed 3D object, and have the 2D network assess the quality of the resulting image, providing feedback to the reconstructor. Different from work based on distillation which produces a single 3D asset for each textual prompt in hours, our approach produces a monocular reconstruction network that can output a controllable 3D asset from a given image, real or generated, in only seconds. Our network can be used for analysis, including monocular reconstruction, or for synthesis, generating articulated assets for real-time applications such as video games.

What does CLIP know about a red circle? Visual prompt engineering for VLMs

Large-scale Vision-Language Models, such as CLIP, learn powerful image-text representations that have found numerous applications, from zero-shot classification to text-to-image generation. Despite that, their capabilities for solving novel discriminative tasks via prompting fall behind those of large language models, such as GPT-3. Here we explore the idea of visual prompt engineering for solving computer vision tasks beyond classification by editing in image space instead of text. In particular, we discover an emergent ability of CLIP, where, by simply drawing a red circle around an object, we can direct the model's attention to that region, while also maintaining global information. We show the power of this simple approach by achieving state-of-the-art in zero-shot referring expressions comprehension and strong performance in keypoint localization tasks. Finally, we draw attention to some potential ethical concerns of large language-vision models.

Training-Free Layout Control with Cross-Attention Guidance

Recent diffusion-based generators can produce high-quality images based only on textual prompts. However, they do not correctly interpret instructions that specify the spatial layout of the composition. We propose a simple approach that can achieve robust layout control without requiring training or fine-tuning the image generator. Our technique, which we call layout guidance, manipulates the cross-attention layers that the model uses to interface textual and visual information and steers the reconstruction in the desired direction given, e.g., a user-specified layout. In order to determine how to best guide attention, we study the role of different attention maps when generating images and experiment with two alternative strategies, forward and backward guidance. We evaluate our method quantitatively and qualitatively with several experiments, validating its effectiveness. We further demonstrate its versatility by extending layout guidance to the task of editing the layout and context of a given real image.

Continual Detection Transformer for Incremental Object Detection

Incremental object detection (IOD) aims to train an object detector in phases, each with annotations for new object categories. As other incremental settings, IOD is subject to catastrophic forgetting, which is often addressed by techniques such as knowledge distillation (KD) and exemplar replay (ER). However, KD and ER do not work well if applied directly to state-of-the-art transformer-based object detectors such as Deformable DETR and UP-DETR. In this paper, we solve these issues by proposing a ContinuaL DEtection TRansformer (CL-DETR), a new method for transformer-based IOD which enables effective usage of KD and ER in this context. First, we introduce a Detector Knowledge Distillation (DKD) loss, focusing on the most informative and reliable predictions from old versions of the model, ignoring redundant background predictions, and ensuring compatibility with the available ground-truth labels. We also improve ER by proposing a calibration strategy to preserve the label distribution of the training set, therefore better matching training and testing statistics. We conduct extensive experiments on COCO 2017 and demonstrate that CL-DETR achieves state-of-the-art results in the IOD setting.

HOLODIFFUSION: Training a 3D Diffusion Model using 2D Images

Diffusion models have emerged as the best approach for generative modeling of 2D images. Part of their success is due to the possibility of training them on millions if not billions of images with a stable learning objective. However, extending these models to 3D remains difficult for two reasons. First, finding a large quantity of 3D training data is much more complex than for 2D images. Second, while it is conceptually trivial to extend the models to operate on 3D rather than 2D grids, the associated cubic growth in memory and compute complexity makes this infeasible. We address the first challenge by introducing a new diffusion setup that can be trained, end-to-end, with only posed 2D images for supervision; and the second challenge by proposing an image formation model that decouples model memory from spatial memory. We evaluate our method on real-world data, using the CO3D dataset which has not been used to train 3D generative models before. We show that our diffusion models are scalable, train robustly, and are competitive in terms of sample quality and fidelity to existing approaches for 3D generative modeling.

Real-time volumetric rendering of dynamic humans

We present a method for fast 3D reconstruction and real-time rendering of dynamic humans from monocular videos with accompanying parametric body fits. Our method can reconstruct a dynamic human in less than 3h using a single GPU, compared to recent state-of-the-art alternatives that take up to 72h. These speedups are obtained by using a lightweight deformation model solely based on linear blend skinning, and an efficient factorized volumetric representation for modeling the shape and color of the person in canonical pose. Moreover, we propose a novel local ray marching rendering which, by exploiting standard GPU hardware and without any baking or conversion of the radiance field, allows visualizing the neural human on a mobile VR device at 40 frames per second with minimal loss of visual quality. Our experimental evaluation shows superior or competitive results with state-of-the art methods while obtaining large training speedup, using a simple model, and achieving real-time rendering.