Skip to content
Model infoModelsSnapshot: 15 Oct 2026

Hyper3D / Deemos / CAST

CAST AlignGen

CAST AlignGen predicts a canonical-space partial point cloud to align a generated object with its observed scene location, orientation and scale.

3D processing
restrictedClosed weights3D processing
Official documentation (opens in a new tab)Reviewed 14 Oct 2026
8 of 23 specification fields collected
Context windowNot collectedAwaiting source review
Maximum outputNot collectedAwaiting source review
Input billingNot collectedHyper3D-associated research publication
Output billingNot collectedNo inferred price

Specifications

Provider-documented facts. “Not collected” means we have not verified that field yet, not that the feature is unsupported.

Context / input limit
Not collected
Maximum input tokens
Not collected
Maximum output
Not collected
Reasoning
Not collected
Tool calling
Not collected
Structured output
Not collected
Streaming
Not collected
Batch processing
Not collected
Fine-tuning
Not collected
Knowledge cutoff
Not collected
Release date
Not collected

Publication or observed application version does not establish an original weight release date.

Parameters
150,000,000Source for Parameters (opens in a new tab)
Architecture
24-layer point-cloud diffusion transformer, width 512; scene points concatenate with noisy samples, geometry latents enter through cross-attention.Source for Architecture (opens in a new tab)
Languages
Not collected
Context caching
Not collected
Usage metering
Not collected

No price or currently callable endpoint for this exact research edition verified. Current Rodin API rates are not inherited.

Data retention
Not collected

No hosting, retention or enterprise contract verified for this research edition.

Input modalities
Scene-space partial point cloud, ObjectGen geometry latentSource for Input modalities (opens in a new tab)
Output modalities
Aligned canonical point cloudSource for Output modalities (opens in a new tab)
Training sequence length
2048 sampled points per training input.Source for Training sequence length (opens in a new tab)
Published training data
200,000 curated Objaverse objects with transformed partial point clouds.Source for Published training data (opens in a new tab)
Training hardware
1500 epochs on 64 NVIDIA A800 GPUs, approximately two days; AdamW learning rate 1e-5.Source for Training hardware (opens in a new tab)
Mesh processing controls
Point correspondences feed the Umeyama algorithm to recover scale, rotation and translation; the neural model does not directly output transform parameters.Source for Mesh processing controls (opens in a new tab)

Access & pricing

Prices belong to an endpoint and billing tier. A provider listing does not guarantee access for every account or region.

Hyper3D-associated research publication

Provider source (opens in a new tab)
API model ID
Not collected

No callable selector or immutable download for this research edition verified.

Access
Research paper/project page. No currently callable endpoint or downloadable weights verified for this exact edition.
Regions
Processing region not established
Endpoint availability
Research edition with no verified public checkpoint download or native API selector.Source for Endpoint availability (opens in a new tab)

Endpoint pricing has not been collected. Check the provider for applicable rates.

Data & enterprise terms

Research access is not assigned the commercial Rodin API retention policy.

Caching

Caching can reuse earlier input processing. Availability, lifetime and billing depend on the endpoint. A cache hit still generates a new response.

01 / INITIAL INPUTProcess & retain

The system processes eligible input and retains reusable state.

02 / LATER REQUESTCheck available state

Reuse depends on matching input, session state and the cache policy.

03 / CACHE HITReuse & generate

Reusing state can reduce repeated work. Any charges follow the billing rules below.

Hyper3D-associated research publication

Not verified

No model-specific prompt-cache contract or price established.

How it works
Not collected

No model-specific prompt-cache contract or price established.

Minimum reusable input
Not collected

No model-specific prompt-cache contract or price established.

Lifetime & refresh
Not collected

No model-specific prompt-cache contract or price established.

How to enable it
Not collected

No model-specific prompt-cache contract or price established.

Usage fields
Not collected

No model-specific prompt-cache contract or price established.

Billing rules
Not collected

No model-specific prompt-cache contract or price established.

Limits & data boundaries
Not collected

No model-specific prompt-cache contract or price established.

No verified cache rate for this endpoint. An empty rate is not a zero charge.

Caching reviewed 14 Oct 2026

What the measurements say

No benchmark observations have been added for this model. We do not turn a vendor description into a performance score.

Latency and throughput depend on the host, request size, reasoning settings and load. There is no measured speed or global usage figure in this record.

The record behind the model

Why it is included

Qualified unreleased-weight classification as reviewed: the official project page does not provide a released weight download, and reviewed provider repository/model listings do not establish one. The paper documents trained models. This does not assert a permanent proprietary license or rule out future releases; public research publication and integration code are not weight releases.

Classification evidence (opens in a new tab)

Lifecycle dates

Research paper first submitted18 Feb 2025Source (opens in a new tab)

Sources reviewed