NeurIPS 2023 Papers

This paper introduces MVDiffusion, a simple yet effective method for generating consistent multi-view images from text prompts given pixel-to-pixel correspondences (e.g., perspective crops from a panorama or multi-view images given depth maps and poses). Unlike prior methods that rely on iterative image warping and inpainting, MVDiffusion simultaneously generates all images with a global awareness, effectively addressing the prevalent error accumulation issue. At its core, MVDiffusion processes perspective images in parallel with a pre-trained text-to-image diffusion model, while integrating novel correspondence-aware attention layers to facilitate cross-view interactions. For panorama generation, while only trained with 10k panoramas, MVDiffusion is able to generate high-resolution photorealistic images for arbitrary texts or extrapolate one perspective image to a 360-degree view. For multi-view depth-to-image generation, MVDiffusion demonstrates state-of-the-art performance for texturing a scene mesh. The project page is at https://mvdiffusion.github.io/.

Achieving machine autonomy and human control often represent divergent objectives in the design of interactive AI systems. Visual generative foundation models such as Stable Diffusion show promise in navigating these goals, especially when prompted with arbitrary languages. However, they often fall short in generating images with spatial, structural, or geometric controls. The integration of such controls, which can accommodate various visual conditions in a single unified model, remains an unaddressed challenge. In response, we introduce UniControl, a new generative foundation model that consolidates a wide array of controllable condition-to-image (C2I) tasks within a singular framework, while still allowing for arbitrary language prompts. UniControl enables pixel-level-precise image generation, where visual conditions primarily influence the generated structures and language prompts guide the style and context. To equip UniControl with the capacity to handle diverse visual conditions, we augment pretrained text-to-image diffusion models and introduce a task-aware HyperNet to modulate the diffusion models, enabling the adaptation to different C2I tasks simultaneously. Trained on nine unique C2I tasks, UniControl demonstrates impressive zero-shot generation abilities with unseen visual conditions. Experimental results show that UniControl often surpasses the performance of single-task-controlled methods of comparable model sizes. This control versatility positions UniControl as a significant advancement in the realm of controllable visual generation.

The blooming progress made in deep learning-based image restoration has been largely attributed to the availability of high-quality, large-scale datasets and advanced network structures. However, optimization functions such as L_1 and L_2 are still de facto. In this study, we propose to investigate new optimization functions to improve image restoration performance. Our key insight is that ``random weight network can be acted as a constraint for training better image restoration networks''. However, not all random weight networks are suitable as constraints. We draw inspiration from Functional theory and show that alternative random weight networks should be represented in the form of a strict mathematical manifold. We explore the potential of our random weight network prototypes that satisfy this requirement: Taylor's unfolding network, invertible neural network, central difference convolution, and zero-order filtering. We investigate these prototypes from four aspects: 1) random weight strategies, 2) network architectures, 3) network depths, and 4) combinations of random weight networks. Furthermore, we devise the random weight in two variants: the weights are randomly initialized only once during the entire training procedure, and the weights are randomly initialized in each training epoch. Our approach can be directly integrated into existing networks without incurring additional training and testing computational costs. We perform extensive experiments across multiple image restoration tasks, including image denoising, low-light image enhancement, and guided image super-resolution to demonstrate the consistent performance gains achieved by our method. Upon acceptance of this paper, we will release the code.

Text-to-image diffusion models can create stunning images from natural language descriptions that rival the work of professional artists and photographers. However, these models are large, with complex network architectures and tens of denoising iterations, making them computationally expensive and slow to run. As a result, high-end GPUs and cloud-based inference are required to run diffusion models at scale. This is costly and has privacy implications, especially when user data is sent to a third party. To overcome these challenges, we present a generic approach that, for the first time, unlocks running text-to-image diffusion models on mobile devices in **less than 2 seconds**. We achieve so by introducing efficient network architecture and improving step distillation. Specifically, we propose an efficient UNet by identifying the redundancy of the original model and reducing the computation of the image decoder via data distillation. Further, we enhance the step distillation by exploring training strategies and introducing regularization from classifier-free guidance. Our extensive experiments on MS-COCO show that our model with $8$ denoising steps achieves better FID and CLIP scores than Stable Diffusion v$1.5$ with $50$ steps. Our work democratizes content creation by bringing powerful text-to-image diffusion models to the hands of users.

Modeling customer shopping intentions is a crucial task for e-commerce, as it directly impacts user experience and engagement. Thus, accurately understanding customer preferences is essential for providing personalized recommendations. Session-based recommendation, which utilizes customer session data to predict their next interaction, has become increasingly popular. However, existing session datasets have limitations in terms of item attributes, user diversity, and dataset scale. As a result, they cannot comprehensively capture the spectrum of user behaviors and preferences. To bridge this gap, we present the Amazon Multilingual Multi-locale Shopping Session Dataset, namely Amazon-M2. It is the first multilingual dataset consisting of millions of user sessions from six different locales, where the major languages of products are English, German, Japanese, French, Italian, and Spanish. Remarkably, the dataset can help us enhance personalization and understanding of user preferences, which can benefit various existing tasks as well as enable new tasks. To test the potential of the dataset, we introduce three tasks in this work: (1) next-product recommendation, (2) next-product recommendation with domain shifts, and (3) next-product title generation. With the above tasks, we benchmark a range of algorithms on our proposed dataset, drawing new insights for further research and practice. In addition, based on the proposed dataset and tasks, we hosted a competition in the KDD CUP 2023 https://www.aicrowd.com/challenges/amazon-kdd-cup-23-multilingual-recommendation-challenge and have attracted thousands of users and submissions. The winning solutions and the associated workshop can be accessed at our website~https://kddcup23.github.io/.

Recent diffusion model advancements have enabled high-fidelity images to be generated using text prompts. However, a domain gap exists between generated images and real-world images, which poses a challenge in generating high-quality variations of real-world images. Our investigation uncovers that this domain gap originates from a latents' distribution gap in different diffusion processes. To address this issue, we propose a novel inference pipeline called Real-world Image Variation by ALignment (RIVAL) that utilizes diffusion models to generate image variations from a single image exemplar. Our pipeline enhances the generation quality of image variations by aligning the image generation process to the source image's inversion chain. Specifically, we demonstrate that step-wise latent distribution alignment is essential for generating high-quality variations. To attain this, we design a cross-image self-attention injection for feature interaction and a step-wise distribution normalization to align the latent features. Incorporating these alignment processes into a diffusion model allows RIVAL to generate high-quality image variations without further parameter optimization. Our experimental results demonstrate that our proposed approach outperforms existing methods concerning semantic similarity and perceptual quality. This generalized inference pipeline can be easily applied to other diffusion-based generation tasks, such as image-conditioned text-to-image generation and stylization. Project page: https://rival-diff.github.io

Utilizing auxiliary outlier datasets to regularize the machine learning model has demonstrated promise for out-of-distribution (OOD) detection and safe prediction. Due to the labor intensity in data collection and cleaning, automating outlier data generation has been a long-desired alternative. Despite the appeal, generating photo-realistic outliers in the high dimensional pixel space has been an open challenge for the field. To tackle the problem, this paper proposes a new framework Dream-OOD, which enables imagining photo-realistic outliers by way of diffusion models, provided with only the in-distribution (ID) data and classes. Specifically, Dream-OOD learns a text-conditioned latent space based on ID data, and then samples outliers in the low-likelihood region via the latent, which can be decoded into images by the diffusion model. Different from prior works [16, 95], Dream-OOD enables visualizing and understanding the imagined outliers, directly in the pixel space. We conduct comprehensive quantitative and qualitative studies to understand the efficacy of Dream-OOD, and show that training with the samples generated by Dream-OOD can significantly benefit OOD detection performance.

Recently, there has been an increasing interest in developing diffusion-based text-to-image generative models capable of generating coherent and well-formed visual text. In this paper, we propose a novel and efficient approach called GlyphControl to address this task. Unlike existing methods that rely on character-aware text encoders like ByT5 and require retraining of text-to-image models, our approach leverages additional glyph conditional information to enhance the performance of the off-the-shelf Stable-Diffusion model in generating accurate visual text. By incorporating glyph instructions, users can customize the content, location, and size of the generated text according to their specific requirements. To facilitate further research in visual text generation, we construct a training benchmark dataset called LAION-Glyph. We evaluate the effectiveness of our approach by measuring OCR-based metrics, CLIP score, and FID of the generated visual text. Our empirical evaluations demonstrate that GlyphControl outperforms the recent DeepFloyd IF approach in terms of OCR accuracy, CLIP score, and FID, highlighting the efficacy of our method.

Measuring the distance between machine-produced and human language is a critical open problem. Inspired by empirical findings from psycholinguistics on the periodicity of entropy in language, we propose FACE, a set of metrics based on Fourier Analysis of the estimated Cross-Entropy of language, for measuring the similarity between model-generated and human-written languages. Based on an open-ended generation task and the experimental data from previous studies, we find that FACE can effectively identify the human-model gap, scales with model size, reflects the outcomes of different sampling methods for decoding, correlates well with other evaluation metrics and with human judgment scores.

In-context vision and language models like Flamingo support arbitrarily interleaved sequences of images and text as input. This format not only enables few-shot learning via interleaving independent supervised (image, text) examples, but also, more complex prompts involving interaction between images, e.g., ``What do image A and image B have in common?'' To support this interface, pretraining occurs over web corpora that similarly contain interleaved images+text. To date, however, large-scale data of this form have not been publicly available. We release Multimodal C4, an augmentation of the popular text-only C4 corpus with images interleaved. We use a linear assignment algorithm to place images into longer bodies of text using CLIP features, a process that we show outperforms alternatives. Multimodal C4 spans everyday topics like cooking, travel, technology, etc. A manual inspection of a random sample of documents shows that a vast majority (88\%) of images are topically relevant, and that linear assignment frequently selects individual sentences specifically well-aligned with each image (80\%). After filtering NSFW images, ads, etc., the resulting corpus consists of 101.2M documents with 571M images interleaved in 43B English tokens.

Maximum likelihood estimation (MLE) is a statistical method used to estimate the parameters of a probability distribution that best explain the observed data. In the context of text generation, MLE is often used to train generative language models, which can then be used to generate new text. However, we argue that MLE is not always necessary and optimal, especially for closed-ended text generation tasks like machine translation. In these tasks, the goal of model is to generate the most appropriate response, which does not necessarily require it to estimate the entire data distribution with MLE. To this end, we propose a novel class of training objectives based on convex functions, which enables text generation models to focus on highly probable outputs without having to estimate the entire data distribution. We investigate the theoretical properties of the optimal predicted distribution when applying convex functions to the loss, demonstrating that convex functions can sharpen the optimal distribution, thereby enabling the model to better capture outputs with high probabilities. Experiments on various text generation tasks and models show the effectiveness of our approach. It enables autoregressive models to bridge the gap between greedy and beam search, and facilitates the learning of non-autoregressive models with a maximum improvement of 9+ BLEU points. Moreover, our approach also exhibits significant impact on large language models (LLMs), substantially enhancing their generative capability on various tasks. Source code is available at \url{https://github.com/ictnlp/Convex-Learning}.

Due to its promising performance, deep hashing has become a prevalent method for approximate nearest neighbors search (ANNs). However, most of current deep hashing methods are validated on relatively small-scale datasets, leaving potential threats when are applied to large-scale real-world scenarios. Specifically, they can be constrained either by the computational cost due to the large number of training categories and samples, or unsatisfactory accuracy. To tackle those issues, we propose a novel deep hashing framework based on product quantization (PQ). It uses a softmax-based differentiable PQ branch to learn a set of predefined PQ codes of the classes. Our method is easy to implement, does not involve large-scale matrix operations, and learns highly discriminate compact codes. We validate our method on multiple large-scaled datasets, including ImageNet100, ImageNet1K, and Glint360K, where the category size scales from 100 to 360K and sample number scales from 10K to 17 million, respectively. Extensive experiments demonstrate the superiority of our method. Code is available at https://github.com/yuleung/FPPQ.

Synthesizing novel view images from a few views is a challenging but practical problem. Existing methods often struggle with producing high-quality results or necessitate per-object optimization in such few-view settings due to the insufficient information provided. In this work, we explore leveraging the strong 2D priors in pre-trained diffusion models for synthesizing novel view images. 2D diffusion models, nevertheless, lack 3D awareness, leading to distorted image synthesis and compromising the identity. To address these problems, we propose $\textit{DreamSparse}$, a framework that enables the frozen pre-trained diffusion model to generate geometry and identity-consistent novel view images. Specifically, DreamSparse incorporates a geometry module designed to capture features about spatial information from sparse views as a 3D prior. Subsequently, a spatial guidance model is introduced to convert rendered feature maps as spatial information for the generative process. This information is then used to guide the pre-trained diffusion model to encourage the synthesis of geometrically consistent images without further tuning. Leveraging the strong image priors in the pre-trained diffusion models, DreamSparse is capable of synthesizing high-quality novel views for both object and object-centric scene-level images and generalising to open-set images. Experimental results demonstrate that our framework can effectively synthesize novel view images from sparse views and outperforms baselines in both trained and open-set category images. More results can be found on our project page: https://sites.google.com/view/dreamsparse-webpage.

Text-conditional diffusion models are able to generate high-fidelity images with diverse contents. However, linguistic representations frequently exhibit ambiguous descriptions of the envisioned objective imagery, requiring the incorporation of additional control signals to bolster the efficacy of text-guided diffusion models. In this work, we propose Cocktail, a pipeline to mix various modalities into one embedding, amalgamated with a generalized ControlNet (gControlNet), a controllable normalisation (ControlNorm), and a spatial guidance sampling method, to actualize multi-modal and spatially-refined control for text-conditional diffusion models. Specifically, we introduce a hyper-network gControlNet, dedicated to the alignment and infusion of the control signals from disparate modalities into the pre-trained diffusion model. gControlNet is capable of accepting flexible modality signals, encompassing the simultaneous reception of any combination of modality signals, or the supplementary fusion of multiple modality signals. The control signals are then fused and injected into the backbone model according to our proposed ControlNorm. Furthermore, our advanced spatial guidance sampling methodology proficiently incorporates the control signal into the designated region, thereby circumventing the manifestation of undesired objects within the generated image. We demonstrate the results of our method in controlling various modalities, proving high-quality synthesis and fidelity to multiple external signals.

Denoising diffusion generative models are capable of generating high-quality data, but suffers from the computation-costly generation process, due to a iterative noise estimation using full-precision networks. As an intuitive solution, quantization can significantly reduce the computational and memory consumption by low-bit parameters and operations. However, low-bit noise estimation networks in diffusion models (DMs) remain unexplored yet and perform much worse than the full-precision counterparts as observed in our experimental studies. In this paper, we first identify that the bottlenecks of low-bit quantized DMs come from a large distribution oscillation on activations and accumulated quantization error caused by the multi-step denoising process. To address these issues, we first develop a Timestep-aware Quantization (TaQ) method and a Noise-estimating Mimicking (NeM) scheme for low-bit quantized DMs (Q-DM) to effectively eliminate such oscillation and accumulated error respectively, leading to well-performed low-bit DMs. In this way, we propose an efficient Q-DM to calculate low-bit DMs by considering both training and inference process in the same framework. We evaluate our methods on popular DDPM and DDIM models. Extensive experimental results show that our method achieves a much better performance than the prior arts. For example, the 4-bit Q-DM theoretically accelerates the 1000-step DDPM by 7.8x and achieves a FID score of 5.17, on the unconditional CIFAR-10 dataset.

Learnt deep neural networks for image super-resolution fail easily if the assumed degradation model in training mismatches that of the real degradation source at the inference stage. Instead of attempting to exhaust all degradation variants in simulation, which is unwieldy and impractical, we propose a novel adversarial neural degradation (AND) model that can, when trained in conjunction with a deep restoration neural network under a minmax criterion, generate a wide range of highly nonlinear complex degradation effects without any explicit supervision. The AND model has a unique advantage over the current state of the art in that it can generalize much better to unseen degradation variants and hence deliver significantly improved restoration performance on real-world images.

We present MindEye, a novel fMRI-to-image approach to retrieve and reconstruct viewed images from brain activity. Our model comprises two parallel submodules that are specialized for retrieval (using contrastive learning) and reconstruction (using a diffusion prior). MindEye can map fMRI brain activity to any high dimensional multimodal latent space, like CLIP image space, enabling image reconstruction using generative models that accept embeddings from this latent space. We comprehensively compare our approach with other existing methods, using both qualitative side-by-side comparisons and quantitative evaluations, and show that MindEye achieves state-of-the-art performance in both reconstruction and retrieval tasks. In particular, MindEye can retrieve the exact original image even among highly similar candidates indicating that its brain embeddings retain fine-grained image-specific information. This allows us to accurately retrieve images even from large-scale databases like LAION-5B. We demonstrate through ablations that MindEye's performance improvements over previous methods result from specialized submodules for retrieval and reconstruction, improved training techniques, and training models with orders of magnitude more parameters. Furthermore, we show that MindEye can better preserve low-level image features in the reconstructions by using img2img, with outputs from a separate autoencoder. All code is available on GitHub.

We present a novel method for reconstructing 3D objects from a single RGB image. Our method leverages the latest image generation models to infer the hidden 3D structure while remaining faithful to the input image. While existing methods obtain impressive results in generating 3D models from text prompts, they do not provide an easy approach for conditioning on input RGB data. Naive extensions of these methods often lead to improper alignment in appearance between the input image and the 3D reconstructions. We address these challenges by introducing Image Constrained Radiance Fields (ConRad), a novel variant of neural radiance fields. ConRad is an efficient 3D representation that explicitly captures the appearance of an input image in one viewpoint. We propose a training algorithm that leverages the single RGB image in conjunction with pretrained Diffusion Models to optimize the parameters of a ConRad representation. Extensive experiments show that ConRad representations can simplify preservation of image details while producing a realistic 3D reconstruction. Compared to existing state-of-the-art baselines, we show that our 3D reconstructions remain more faithful to the input and produce more consistent 3D models while demonstrating significantly improved quantitative performance on a ShapeNet object benchmark.

We present \emph{DreamHuman}, a method to generate realistic animatable 3D human avatar models entirely from textual descriptions. Recent text-to-3D methods have made considerable strides in generation, but are still lacking in important aspects. Control and often spatial resolution remain limited, existing methods produce fixed rather than 3D human models that can be placed in different poses (i.e. re-posable or animatable), and anthropometric consistency for complex structures like people remains a challenge. \emph{DreamHuman} connects large text-to-image synthesis models, neural radiance fields, and statistical human body models in a novel optimization framework. This makes it possible to generate dynamic 3D human avatars with high-quality textures and learnt per-instance rigid and non rigid geometric deformations. We demonstrate that our method is capable to generate a wide variety of animatable, realistic 3D human models from text. These have diverse appearance, clothing, skin tones and body shapes, and outperform both generic text-to-3D approaches and previous text-based 3D avatar generators in visual fidelity.